README.md

Crawl and Visualize ICLR 2019 OpenReview Data

Descriptions

This Jupyter Notebook contains the data and visualizations that are crawled ICLR 2019 OpenReview webpages. All the crawled data (sorted by the average ratings) can be found here. The accepted papers have an average rating of 6.611 and 4.716 for rejected papers. The distributions are plotted as follows.

Prerequisites

• Python3.5
• selenium
• pyvirtualdisplay (run on a headless device)
• wordcloud
• imageio

Visualizations

The word clouds formed by keywords of submissions show the hot topics including reinforcement learning, generative adversarial networks, generative models, imitation learning, representation learning, etc.

This figure is plotted with python word cloud generator

from wordcloud import WordCloud
wordcloud = WordCloud(max_font_size=64, max_words=160, 
                      width=1280, height=640,
                      background_color="black").generate(' '.join(keywords))
plt.figure(figsize=(16, 8))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.show()

The distributions of reviewer ratings center around 5 to 6 (mean: 5.15).

You can compute how many papers are beaten by yours with

def PR(rating_mean, your_rating):
    pr = np.sum(your_rating >= np.array(rating_mean))/len(rating_mean)*100
    return pr
my_rating = (5+6+7)/3  # your average rating here
print('Your papar beats {:.2f}% of submission '
      '(well, jsut based on the ratings...)'.format(PR(rating_mean, my_rating)))
# ICLR 2017: accept rate 39.1% (198/507) (15 orals and 183 posters)
# ICLR 2018: accept rate 32% (314/981) (23 orals and 291 posters)
# ICLR 2018: accept rate ?% (?/1580)

The top 50 common keywords and their frequency.

The average reviewer ratings and the frequency of keywords indicate that to maximize your chance to get higher ratings would be using the keywords such as theory, robustness, or graph neural network.

How it works

See How to install Selenium and ChromeDriver on Ubuntu.

To crawl data from dynamic websites such as OpenReview, a headless web simulator is created by

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
executable_path = '/Users/waltersun/Desktop/chromedriver'  # path to your executable browser
options = Options()
options.add_argument("--headless")
browser = webdriver.Chrome(options=options, executable_path=executable_path)  

Then, we can get the content of a webpage

browser.get(url)

To know what content we can crawl, we will need to inspect the webpage layout.

I chose to get the content by

key = browser.find_elements_by_class_name("note_content_field")
value = browser.find_elements_by_class_name("note_content_value")

The data includes the abstract, keywords, TL; DR, comments.

Installing Selenium and ChromeDriver on Ubuntu

The following content is hugely borrowed from a nice post written by Christopher Su.

• Install Google Chrome for Debian/Ubuntu

sudo apt-get install libxss1 libappindicator1 libindicator7
wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb

sudo dpkg -i google-chrome*.deb
sudo apt-get install -f

• Install xvfb to run Chrome on a headless device

sudo apt-get install xvfb

• Install ChromeDriver for 64-bit Linux

sudo apt-get install unzip  # If you don't have unzip package

wget -N http://chromedriver.storage.googleapis.com/2.26/chromedriver_linux64.zip
unzip chromedriver_linux64.zip
chmod +x chromedriver

sudo mv -f chromedriver /usr/local/share/chromedriver
sudo ln -s /usr/local/share/chromedriver /usr/local/bin/chromedriver
sudo ln -s /usr/local/share/chromedriver /usr/bin/chromedriver

If your system is 32-bit, please find the ChromeDriver releases here and modify the above download command.

• Install Python dependencies (Selenium and pyvirtualdisplay)

pip install pyvirtualdisplay selenium

• Test your setup in Python

from pyvirtualdisplay import Display
from selenium import webdriver

display = Display(visible=0, size=(1024, 1024))
display.start()
browser = webdriver.Chrome()
browser.get('http://shaohua0116.github.io/')
print(browser.title)
print(browser.find_element_by_class_name('bio').text)

All ICLR 2019 OpenReview data

Collected at 2019-12-05 11:31:13.692315

Number of submissions: 1579 (withdrawn submissions: 0)

Rank	Average Rating	Title	Ratings	Variance	Decision
1	8.67	Generating High Fidelity Images With Subscale Pixel Networks And Multidimensional Upscaling	7, 10, 9	1.25	Accept (Oral)
2	8.67	Alista: Analytic Weights Are As Good As Learned Weights In Lista	10, 7, 9	1.25	Accept (Poster)
3	8.33	Benchmarking Neural Network Robustness To Common Corruptions And Perturbations	7, 9, 9	0.94	Accept (Poster)
4	8.33	On Random Deep Weight-tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, And Implications To Training	9, 8, 8	0.47	Accept (Oral)
5	8.00	Posterior Attention Models For Sequence To Sequence Learning	8, 9, 7	0.82	Accept (Poster)
6	8.00	Pay Less Attention With Lightweight And Dynamic Convolutions	8, 8, 8	0.00	Accept (Oral)
7	8.00	Slimmable Neural Networks	8, 9, 7	0.82	Accept (Poster)
8	8.00	A Unified Theory Of Early Visual Representations From Retina To Cortex Through Anatomically Constrained Deep Cnns	8, 8, 8	0.00	Accept (Oral)
9	8.00	Ordered Neurons: Integrating Tree Structures Into Recurrent Neural Networks	9, 7, 8	0.82	Accept (Oral)
10	8.00	Temporal Difference Variational Auto-encoder	8, 9, 7	0.82	Accept (Oral)
11	8.00	Enabling Factorized Piano Music Modeling And Generation With The Maestro Dataset	8, 8, 8	0.00	Accept (Oral)
12	8.00	Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse Rl, And Gans By Constraining Information Flow	6, 10, 8	1.63	Accept (Poster)
13	8.00	Near-optimal Representation Learning For Hierarchical Reinforcement Learning	8, 9, 7	0.82	Accept (Poster)
14	8.00	Ba-net: Dense Bundle Adjustment Networks	9, 7, 8	0.82	Accept (Oral)
15	8.00	Understanding And Improving Interpolation In Autoencoders Via An Adversarial Regularizer	7, 8, 9	0.82	Accept (Poster)
16	8.00	Snip: Single-shot Network Pruning Based On Connection Sensitivity	8, 7, 9	0.82	Accept (Poster)
17	8.00	Meta-learning Update Rules For Unsupervised Representation Learning	8, 8, 8	0.00	Accept (Oral)
18	8.00	Large Scale Gan Training For High Fidelity Natural Image Synthesis	8, 7, 9	0.82	Accept (Oral)
19	8.00	Unsupervised Learning Of The Set Of Local Maxima	8, 8, 8	0.00	Accept (Poster)
20	8.00	An Empirical Study Of Example Forgetting During Deep Neural Network Learning	9, 8, 7	0.82	Accept (Poster)
21	7.67	Learning Robust Representations By Projecting Superficial Statistics Out	7, 7, 9	0.94	Accept (Oral)
22	7.67	Automatically Composing Representation Transformations As A Means For Generalization	7, 9, 7	0.94	Accept (Poster)
23	7.67	Identifying And Controlling Important Neurons In Neural Machine Translation	7, 10, 6	1.70	Accept (Poster)
24	7.67	Towards Robust, Locally Linear Deep Networks	8, 8, 7	0.47	Accept (Poster)
25	7.67	Deep Decoder: Concise Image Representations From Untrained Non-convolutional Networks	8, 8, 7	0.47	Accept (Poster)
26	7.67	Lagging Inference Networks And Posterior Collapse In Variational Autoencoders	7, 8, 8	0.47	Accept (Poster)
27	7.67	A Variational Inequality Perspective On Generative Adversarial Networks	8, 8, 7	0.47	Accept (Poster)
28	7.67	Robustness May Be At Odds With Accuracy	8, 7, 8	0.47	Accept (Poster)
29	7.67	Knockoffgan: Generating Knockoffs For Feature Selection Using Generative Adversarial Networks	6, 10, 7	1.70	Accept (Oral)
30	7.67	Adaptive Input Representations For Neural Language Modeling	7, 8, 8	0.47	Accept (Poster)
31	7.67	The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks	5, 9, 9	1.89	Accept (Oral)
32	7.67	Critical Learning Periods In Deep Networks	9, 8, 6	1.25	Accept (Poster)
33	7.67	Composing Complex Skills By Learning Transition Policies	7, 9, 7	0.94	Accept (Poster)
34	7.67	Supervised Community Detection With Line Graph Neural Networks	6, 9, 8	1.25	Accept (Poster)
35	7.67	Learning Deep Representations By Mutual Information Estimation And Maximization	7, 7, 9	0.94	Accept (Oral)
36	7.67	Smoothing The Geometry Of Probabilistic Box Embeddings	8, 8, 7	0.47	Accept (Oral)
37	7.67	A2bcd: Asynchronous Acceleration With Optimal Complexity	7, 7, 9	0.94	Accept (Poster)
38	7.67	Kernel Change-point Detection With Auxiliary Deep Generative Models	8, 8, 7	0.47	Accept (Poster)
39	7.67	Imagenet-trained Cnns Are Biased Towards Texture; Increasing Shape Bias Improves Accuracy And Robustness	7, 8, 8	0.47	Accept (Oral)
40	7.67	Slalom: Fast, Verifiable And Private Execution Of Neural Networks In Trusted Hardware	7, 7, 9	0.94	Accept (Oral)
41	7.67	Sparse Dictionary Learning By Dynamical Neural Networks	6, 9, 8	1.25	Accept (Poster)
42	7.50	On The Minimal Supervision For Training Any Binary Classifier From Only Unlabeled Data	7, 8, 8, 7	0.50	Accept (Poster)
43	7.50	Exploration By Random Network Distillation	4, 9, 10, 7	2.29	Accept (Poster)
44	7.33	Dimensionality Reduction For Representing The Knowledge Of Probabilistic Models	6, 7, 9	1.25	Accept (Poster)
45	7.33	Probabilistic Recursive Reasoning For Multi-agent Reinforcement Learning	8, 7, 7	0.47	Accept (Poster)
46	7.33	Approximability Of Discriminators Implies Diversity In Gans	8, 7, 7	0.47	Accept (Poster)
47	7.33	Evaluating Robustness Of Neural Networks With Mixed Integer Programming	7, 8, 7	0.47	Accept (Poster)
48	7.33	Biologically-plausible Learning Algorithms Can Scale To Large Datasets	9, 9, 4	2.36	Accept (Poster)
49	7.33	Diagnosing And Enhancing Vae Models	9, 6, 7	1.25	Accept (Poster)
50	7.33	Learning To Navigate The Web	7, 8, 7	0.47	Accept (Poster)
51	7.33	Transferring Knowledge Across Learning Processes	6, 8, 8	0.94	Accept (Oral)
52	7.33	Improving Differentiable Neural Computers Through Memory Masking, De-allocation, And Link Distribution Sharpness Control	8, 7, 7	0.47	Accept (Poster)
53	7.33	Towards Metamerism Via Foveated Style Transfer	7, 8, 7	0.47	Accept (Poster)
54	7.33	Variance Reduction For Reinforcement Learning In Input-driven Environments	7, 9, 6	1.25	Accept (Poster)
55	7.33	Quaternion Recurrent Neural Networks	8, 7, 7	0.47	Accept (Poster)
56	7.33	Promp: Proximal Meta-policy Search	6, 7, 9	1.25	Accept (Poster)
57	7.33	Label Super-resolution Networks	7, 6, 9	1.25	Accept (Poster)
58	7.33	Learning Self-imitating Diverse Policies	8, 6, 8	0.94	Accept (Poster)
59	7.33	Learning Protein Sequence Embeddings Using Information From Structure	7, 7, 8	0.47	Accept (Poster)
60	7.33	Diffusion Scattering Transforms On Graphs	6, 9, 7	1.25	Accept (Poster)
61	7.33	Deep Frank-wolfe For Neural Network Optimization	7, 7, 8	0.47	Accept (Poster)
62	7.33	Gradient Descent Aligns The Layers Of Deep Linear Networks	7, 9, 6	1.25	Accept (Poster)
63	7.33	Recurrent Experience Replay In Distributed Reinforcement Learning	7, 7, 8	0.47	Accept (Poster)
64	7.33	Large-scale Study Of Curiosity-driven Learning	6, 9, 7	1.25	Accept (Poster)
65	7.33	Learning Localized Generative Models For 3d Point Clouds Via Graph Convolution	9, 6, 7	1.25	Accept (Poster)
66	7.33	Prior Convictions: Black-box Adversarial Attacks With Bandits And Priors	7, 8, 7	0.47	Accept (Poster)
67	7.33	Learning Latent Superstructures In Variational Autoencoders For Deep Multidimensional Clustering	8, 7, 7	0.47	Accept (Poster)
68	7.33	Learning Grid Cells As Vector Representation Of Self-position Coupled With Matrix Representation Of Self-motion	8, 7, 7	0.47	Accept (Poster)
69	7.33	Clarinet: Parallel Wave Generation In End-to-end Text-to-speech	9, 6, 7	1.25	Accept (Poster)
70	7.33	Dynamic Sparse Graph For Efficient Deep Learning	8, 7, 7	0.47	Accept (Poster)
71	7.33	Learning To Remember More With Less Memorization	7, 8, 7	0.47	Accept (Oral)
72	7.33	Gan Dissection: Visualizing And Understanding Generative Adversarial Networks	7, 7, 8	0.47	Accept (Poster)
73	7.33	Detecting Egregious Responses In Neural Sequence-to-sequence Models	7, 7, 8	0.47	Accept (Poster)
74	7.33	Deep Layers As Stochastic Solvers	7, 7, 8	0.47	Accept (Poster)
75	7.33	Small Nonlinearities In Activation Functions Create Bad Local Minima In Neural Networks	7, 7, 8	0.47	Accept (Poster)
76	7.33	Efficient Training On Very Large Corpora Via Gramian Estimation	7, 8, 7	0.47	Accept (Poster)
77	7.33	Diversity Is All You Need: Learning Skills Without A Reward Function	8, 7, 7	0.47	Accept (Poster)
78	7.33	Instagan: Instance-aware Image-to-image Translation	7, 8, 7	0.47	Accept (Poster)
79	7.33	Time-agnostic Prediction: Predicting Predictable Video Frames	7, 8, 7	0.47	Accept (Poster)
80	7.33	Learning To Schedule Communication In Multi-agent Reinforcement Learning	7, 8, 7	0.47	Accept (Poster)
81	7.33	No Training Required: Exploring Random Encoders For Sentence Classification	7, 7, 8	0.47	Accept (Poster)
82	7.33	Lanczosnet: Multi-scale Deep Graph Convolutional Networks	7, 7, 8	0.47	Accept (Poster)
83	7.33	The Neuro-symbolic Concept Learner: Interpreting Scenes, Words, And Sentences From Natural Supervision	7, 6, 9	1.25	Accept (Oral)
84	7.33	How Powerful Are Graph Neural Networks?	7, 7, 8	0.47	Accept (Oral)
85	7.25	Episodic Curiosity Through Reachability	7, 8, 6, 8	0.83	Accept (Poster)
86	7.00	Strokenet: A Neural Painting Environment	7, 8, 6	0.82	Accept (Poster)
87	7.00	Discriminator-actor-critic: Addressing Sample Inefficiency And Reward Bias In Adversarial Imitation Learning	8, 6, 7	0.82	Accept (Poster)
88	7.00	An Analytic Theory Of Generalization Dynamics And Transfer Learning In Deep Linear Networks	8, 7, 6	0.82	Accept (Poster)
89	7.00	Feature Intertwiner For Object Detection	5, 9, 7	1.63	Accept (Poster)
90	7.00	Learning Neural Pde Solvers With Convergence Guarantees	7, 8, 6	0.82	Accept (Poster)
91	7.00	Knowledge Flow: Improve Upon Your Teachers	6, 8, 7	0.82	Accept (Poster)
92	7.00	Multilingual Neural Machine Translation With Knowledge Distillation	7, 7, 7	0.00	Accept (Poster)
93	7.00	Texttovec: Deep Contextualized Neural Autoregressive Topic Models Of Language With Distributed Compositional Prior	7, 8, 6	0.82	Accept (Poster)
94	7.00	Supervised Policy Update For Deep Reinforcement Learning	9, 6, 6	1.41	Accept (Poster)
95	7.00	Gansynth: Adversarial Neural Audio Synthesis	6, 7, 8	0.82	Accept (Poster)
96	7.00	Lemonade: Learned Motif And Neuronal Assembly Detection In Calcium Imaging Videos	8, 5, 8	1.41	Accept (Poster)
97	7.00	The Comparative Power Of Relu Networks And Polynomial Kernels In The Presence Of Sparse Latent Structure	7, 7, 7	0.00	Accept (Poster)
98	7.00	Execution-guided Neural Program Synthesis	7, 7, 7	0.00	Accept (Poster)
99	7.00	Deterministic Variational Inference For Robust Bayesian Neural Networks	7, 7, 7	0.00	Accept (Oral)
100	7.00	Distributional Concavity Regularization For Gans	7, 8, 6, 7	0.71	Accept (Poster)
101	7.00	Som-vae: Interpretable Discrete Representation Learning On Time Series	9, 6, 6	1.41	Accept (Poster)
102	7.00	Variational Autoencoders With Jointly Optimized Latent Dependency Structure	7, 6, 8	0.82	Accept (Poster)
103	7.00	Learning Sparse Relational Transition Models	6, 7, 8	0.82	Accept (Poster)
104	7.00	Adversarial Domain Adaptation For Stable Brain-machine Interfaces	9, 5, 7	1.63	Accept (Poster)
105	7.00	The Role Of Over-parametrization In Generalization Of Neural Networks	7, 7, 7	0.00	Accept (Poster)
106	7.00	Differentiable Learning-to-normalize Via Switchable Normalization	7, 7, 7	0.00	Accept (Poster)
107	7.00	Stochastic Optimization Of Sorting Networks Via Continuous Relaxations	8, 7, 6	0.82	Accept (Poster)
108	7.00	A Statistical Approach To Assessing Neural Network Robustness	6, 7, 8	0.82	Accept (Poster)
109	7.00	Darts: Differentiable Architecture Search	6, 7, 8	0.82	Accept (Poster)
110	7.00	Learning Concise Representations For Regression By Evolving Networks Of Trees	7, 6, 8	0.82	Accept (Poster)
111	7.00	Padam: Closing The Generalization Gap Of Adaptive Gradient Methods In Training Deep Neural Networks	6, 6, 9	1.41	Reject
112	7.00	A Universal Music Translation Network	8, 7, 6	0.82	Accept (Poster)
113	7.00	Deep Learning 3d Shapes Using Alt-az Anisotropic 2-sphere Convolution	6, 8, 7	0.82	Accept (Poster)
114	7.00	Energy-constrained Compression For Deep Neural Networks Via Weighted Sparse Projection And Layer Input Masking	7, 7, 7	0.00	Accept (Poster)
115	7.00	Deep Graph Infomax	9, 5, 7	1.63	Accept (Poster)
116	7.00	On The Universal Approximability And Complexity Bounds Of Quantized Relu Neural Networks	7, 6, 8	0.82	Accept (Poster)
117	7.00	Global-to-local Memory Pointer Networks For Task-oriented Dialogue	8, 8, 5	1.41	Accept (Poster)
118	7.00	Self-monitoring Navigation Agent Via Auxiliary Progress Estimation	8, 6, 7	0.82	Accept (Poster)
119	7.00	Signsgd Via Zeroth-order Oracle	8, 7, 6	0.82	Accept (Poster)
120	7.00	Learning Particle Dynamics For Manipulating Rigid Bodies, Deformable Objects, And Fluids	8, 6, 7	0.82	Accept (Poster)
121	7.00	Generative Code Modeling With Graphs	7, 7, 7	0.00	Accept (Poster)
122	7.00	The Deep Weight Prior	6, 8, 7	0.82	Accept (Poster)
123	7.00	Bounce And Learn: Modeling Scene Dynamics With Real-world Bounces	6, 7, 8	0.82	Accept (Poster)
124	7.00	Quasi-hyperbolic Momentum And Adam For Deep Learning	7, 6, 8	0.82	Accept (Poster)
125	7.00	Integer Networks For Data Compression With Latent-variable Models	6, 7, 8	0.82	Accept (Poster)
126	7.00	Deep Online Learning Via Meta-learning: Continual Adaptation For Model-based Rl	7, 7, 7	0.00	Accept (Poster)
127	7.00	Are Adversarial Examples Inevitable?	7, 8, 6	0.82	Accept (Poster)
128	7.00	Learning To Screen For Fast Softmax Inference On Large Vocabulary Neural Networks	7, 6, 8	0.82	Accept (Poster)
129	7.00	Information-directed Exploration For Deep Reinforcement Learning	7, 7, 7	0.00	Accept (Poster)
130	7.00	Rotdcf: Decomposition Of Convolutional Filters For Rotation-equivariant Deep Networks	7, 7, 7	0.00	Accept (Poster)
131	7.00	Theoretical Analysis Of Auto Rate-tuning By Batch Normalization	7, 7, 7	0.00	Accept (Poster)
132	7.00	Visual Semantic Navigation Using Scene Priors	7, 7, 7	0.00	Accept (Poster)
133	7.00	Woulda, Coulda, Shoulda: Counterfactually-guided Policy Search	7, 7, 7	0.00	Accept (Poster)
134	7.00	Function Space Particle Optimization For Bayesian Neural Networks	7, 7, 7	0.00	Accept (Poster)
135	7.00	Eidetic 3d Lstm: A Model For Video Prediction And Beyond	7, 7, 7	0.00	Accept (Poster)
136	7.00	Wizard Of Wikipedia: Knowledge-powered Conversational Agents	7, 6, 8	0.82	Accept (Poster)
137	7.00	Meta-learning Probabilistic Inference For Prediction	7, 6, 8	0.82	Accept (Poster)
138	7.00	Don't Settle For Average, Go For The Max: Fuzzy Sets And Max-pooled Word Vectors	8, 8, 5	1.41	Accept (Poster)
139	7.00	Solving The Rubik's Cube With Approximate Policy Iteration	7, 7, 7	0.00	Accept (Poster)
140	7.00	Learning A Meta-solver For Syntax-guided Program Synthesis	7, 7, 7	0.00	Accept (Poster)
141	7.00	Rotate: Knowledge Graph Embedding By Relational Rotation In Complex Space	7, 7, 7	0.00	Accept (Poster)
142	7.00	Generative Question Answering: Learning To Answer The Whole Question	7, 6, 8	0.82	Accept (Poster)
143	7.00	Local Sgd Converges Fast And Communicates Little	8, 5, 8	1.41	Accept (Poster)
144	7.00	Ffjord: Free-form Continuous Dynamics For Scalable Reversible Generative Models	7, 7, 7	0.00	Accept (Oral)
145	7.00	Adashift: Decorrelation And Convergence Of Adaptive Learning Rate Methods	6, 6, 9	1.41	Accept (Poster)
146	7.00	What Do You Learn From Context? Probing For Sentence Structure In Contextualized Word Representations	7, 7, 7	0.00	Accept (Poster)
147	7.00	Modeling Uncertainty With Hedged Instance Embeddings	7, 7, 7	0.00	Accept (Poster)
148	7.00	Learning Implicitly Recurrent Cnns Through Parameter Sharing	8, 7, 6	0.82	Accept (Poster)
149	7.00	Arm: Augment-reinforce-merge Gradient For Stochastic Binary Networks	8, 6, 7	0.82	Accept (Poster)
150	7.00	On The Loss Landscape Of A Class Of Deep Neural Networks With No Bad Local Valleys	7, 8, 6	0.82	Accept (Poster)
151	7.00	Riemannian Adaptive Optimization Methods	7, 7, 7	0.00	Accept (Poster)
152	7.00	Learning To Learn Without Forgetting By Maximizing Transfer And Minimizing Interference	6, 8, 7	0.82	Accept (Poster)
153	7.00	G-sgd: Optimizing Relu Neural Networks In Its Positively Scale-invariant Space	7, 7, 7	0.00	Accept (Poster)
154	7.00	Reasoning About Physical Interactions With Object-oriented Prediction And Planning	5, 7, 9	1.63	Accept (Poster)
155	7.00	Hindsight Policy Gradients	7, 7, 7	0.00	Accept (Poster)
156	7.00	Unsupervised Domain Adaptation For Distance Metric Learning	8, 5, 8	1.41	Accept (Poster)
157	7.00	Learning Mixed-curvature Representations In Product Spaces	7, 7, 7	0.00	Accept (Poster)
158	7.00	Auxiliary Variational Mcmc	7, 7, 7	0.00	Accept (Poster)
159	7.00	Unsupervised Speech Recognition Via Segmental Empirical Output Distribution Matching	7, 7, 7	0.00	Accept (Poster)
160	7.00	On Computation And Generalization Of Generative Adversarial Networks Under Spectrum Control	8, 6, 7	0.82	Accept (Poster)
161	7.00	Optimal Control Via Neural Networks: A Convex Approach	6, 8, 7	0.82	Accept (Poster)
162	7.00	Whitening And Coloring Batch Transform For Gans	7, 7, 7	0.00	Accept (Poster)
163	7.00	Deep, Skinny Neural Networks Are Not Universal Approximators	6, 8, 7	0.82	Accept (Poster)
164	7.00	Nadpex: An On-policy Temporally Consistent Exploration Method For Deep Reinforcement Learning	8, 6, 7	0.82	Accept (Poster)
165	7.00	Learning To Solve Circuit-sat: An Unsupervised Differentiable Approach	6, 8, 7	0.82	Accept (Poster)
166	7.00	A Convergence Analysis Of Gradient Descent For Deep Linear Neural Networks	7, 7, 7	0.00	Accept (Poster)
167	7.00	Learning A Sat Solver From Single-bit Supervision	7, 7, 7	0.00	Accept (Poster)
168	7.00	Generating Multiple Objects At Spatially Distinct Locations	6, 8, 7	0.82	Accept (Poster)
169	7.00	K For The Price Of 1: Parameter-efficient Multi-task And Transfer Learning	7, 6, 8	0.82	Accept (Poster)
170	7.00	Bias-reduced Uncertainty Estimation For Deep Neural Classifiers	7, 7, 7	0.00	Accept (Poster)
171	7.00	Probabilistic Neural-symbolic Models For Interpretable Visual Question Answering	8, 6, 7	0.82	Reject
172	7.00	Representation Degeneration Problem In Training Natural Language Generation Models	7, 7, 7	0.00	Accept (Poster)
173	7.00	Neural Network Gradient-based Learning Of Black-box Function Interfaces	7, 7, 7	0.00	Accept (Poster)
174	7.00	A Data-driven And Distributed Approach To Sparse Signal Representation And Recovery	8, 7, 6	0.82	Accept (Poster)
175	7.00	Relaxed Quantization For Discretized Neural Networks	7, 7, 7	0.00	Accept (Poster)
176	7.00	Invariant And Equivariant Graph Networks	8, 4, 9	2.16	Accept (Poster)
177	7.00	Dyrep: Learning Representations Over Dynamic Graphs	6, 7, 8	0.82	Accept (Poster)
178	7.00	The Laplacian In Rl: Learning Representations With Efficient Approximations	7, 7, 7	0.00	Accept (Poster)
179	7.00	Learning Recurrent Binary/ternary Weights	6, 8, 7	0.82	Accept (Poster)
180	7.00	How Important Is A Neuron	7, 7, 7	0.00	Accept (Poster)
181	6.80	Subgradient Descent Learns Orthogonal Dictionaries	7, 7, 7, 7, 6	0.40	Accept (Poster)
182	6.75	Unsupervised Learning Via Meta-learning	7, 6, 8, 6	0.83	Accept (Poster)
183	6.75	Bayesian Deep Convolutional Networks With Many Channels Are Gaussian Processes	7, 7, 7, 6	0.43	Accept (Poster)
184	6.75	Deterministic Pac-bayesian Generalization Bounds For Deep Networks Via Generalizing Noise-resilience	8, 7, 7, 5	1.09	Accept (Poster)
185	6.67	Structured Adversarial Attack: Towards General Implementation And Better Interpretability	7, 7, 6	0.47	Accept (Poster)
186	6.67	Adaptive Estimators Show Information Compression In Deep Neural Networks	7, 6, 7	0.47	Accept (Poster)
187	6.67	Tree-structured Recurrent Switching Linear Dynamical Systems For Multi-scale Modeling	7, 7, 6	0.47	Accept (Poster)
188	6.67	Residual Non-local Attention Networks For Image Restoration	7, 7, 6	0.47	Accept (Poster)
189	6.67	Cem-rl: Combining Evolutionary And Gradient-based Methods For Policy Search	6, 7, 7	0.47	Accept (Poster)
190	6.67	Marginal Policy Gradients: A Unified Family Of Estimators For Bounded Action Spaces With Applications	7, 6, 7	0.47	Accept (Poster)
191	6.67	Relgan: Relational Generative Adversarial Networks For Text Generation	6, 8, 6	0.94	Accept (Poster)
192	6.67	Defensive Quantization: When Efficiency Meets Robustness	7, 6, 7	0.47	Accept (Poster)
193	6.67	Policy Transfer With Strategy Optimization	7, 7, 6	0.47	Accept (Poster)
194	6.67	Big-little Net: An Efficient Multi-scale Feature Representation For Visual And Speech Recognition	7, 6, 7	0.47	Accept (Poster)
195	6.67	Universal Transformers	6, 6, 8	0.94	Accept (Poster)
196	6.67	Active Learning With Partial Feedback	7, 6, 7	0.47	Accept (Poster)
197	6.67	There Are Many Consistent Explanations Of Unlabeled Data: Why You Should Average	6, 8, 6	0.94	Accept (Poster)
198	6.67	Unsupervised Control Through Non-parametric Discriminative Rewards	8, 5, 7	1.25	Accept (Poster)
199	6.67	On The Convergence Of A Class Of Adam-type Algorithms For Non-convex Optimization	7, 7, 6	0.47	Accept (Poster)
200	6.67	Adaptivity Of Deep Relu Network For Learning In Besov And Mixed Smooth Besov Spaces: Optimal Rate And Curse Of Dimensionality	8, 6, 6	0.94	Accept (Poster)
201	6.67	Predicting The Generalization Gap In Deep Networks With Margin Distributions	5, 9, 6	1.70	Accept (Poster)
202	6.67	A Mean Field Theory Of Batch Normalization	7, 6, 7	0.47	Accept (Poster)
203	6.67	Don't Let Your Discriminator Be Fooled	7, 7, 6	0.47	Accept (Poster)
204	6.67	L-shapley And C-shapley: Efficient Model Interpretation For Structured Data	7, 7, 6	0.47	Accept (Poster)
205	6.67	Hyperbolic Attention Networks	6, 7, 7	0.47	Accept (Poster)
206	6.67	Learning To Make Analogies By Contrasting Abstract Relational Structure	6, 7, 7	0.47	Accept (Poster)
207	6.67	Meta-learning For Stochastic Gradient Mcmc	7, 7, 6	0.47	Accept (Poster)
208	6.67	Directed-info Gail: Learning Hierarchical Policies From Unsegmented Demonstrations Using Directed Information	6, 6, 8	0.94	Accept (Poster)
209	6.67	Building Dynamic Knowledge Graphs From Text Using Machine Reading Comprehension	6, 7, 7	0.47	Accept (Poster)
210	6.67	Proxquant: Quantized Neural Networks Via Proximal Operators	8, 7, 5	1.25	Accept (Poster)
211	6.67	Emergent Coordination Through Competition	7, 7, 6	0.47	Accept (Poster)
212	6.67	Doubly Reparameterized Gradient Estimators For Monte Carlo Objectives	7, 7, 6	0.47	Accept (Poster)
213	6.67	Learning To Understand Goal Specifications By Modelling Reward	7, 7, 6	0.47	Accept (Poster)
214	6.67	Off-policy Evaluation And Learning From Logged Bandit Feedback: Error Reduction Via Surrogate Policy	6, 8, 6	0.94	Accept (Poster)
215	6.67	Improving Mmd-gan Training With Repulsive Loss Function	6, 7, 7	0.47	Accept (Poster)
216	6.67	Probgan: Towards Probabilistic Gan With Theoretical Guarantees	6, 5, 9	1.70	Accept (Poster)
217	6.67	Three Mechanisms Of Weight Decay Regularization	6, 7, 7	0.47	Accept (Poster)
218	6.67	Hierarchical Rl Using An Ensemble Of Proprioceptive Periodic Policies	6, 7, 7	0.47	Accept (Poster)
219	6.67	Detecting Adversarial Examples Via Neural Fingerprinting	5, 9, 6	1.70	Reject
220	6.67	Diversity-sensitive Conditional Generative Adversarial Networks	7, 6, 7	0.47	Accept (Poster)
221	6.67	Optimal Completion Distillation For Sequence Learning	7, 7, 6	0.47	Accept (Poster)
222	6.67	Flowqa: Grasping Flow In History For Conversational Machine Comprehension	7, 6, 7	0.47	Accept (Poster)
223	6.67	Towards The First Adversarially Robust Neural Network Model On Mnist	7, 7, 6	0.47	Accept (Poster)
224	6.67	Sample Efficient Adaptive Text-to-speech	7, 7, 6	0.47	Accept (Poster)
225	6.67	Latent Convolutional Models	6, 7, 7	0.47	Accept (Poster)
226	6.67	Minimal Images In Deep Neural Networks: Fragile Object Recognition In Natural Images	7, 7, 6	0.47	Accept (Poster)
227	6.67	Universal Stagewise Learning For Non-convex Problems With Convergence On Averaged Solutions	8, 6, 6	0.94	Accept (Poster)
228	6.67	Learning Multimodal Graph-to-graph Translation For Molecule Optimization	7, 7, 6	0.47	Accept (Poster)
229	6.67	Autoloss: Learning Discrete Schedule For Alternate Optimization	7, 6, 7	0.47	Accept (Poster)
230	6.67	Efficient Lifelong Learning With A-gem	7, 6, 7	0.47	Accept (Poster)
231	6.67	Spherical Cnns On Unstructured Grids	6, 7, 7	0.47	Accept (Poster)
232	6.67	Differentiable Perturb-and-parse: Semi-supervised Parsing With A Structured Variational Autoencoder	8, 7, 5	1.25	Accept (Poster)
233	6.67	Practical Lossless Compression With Latent Variables Using Bits Back Coding	6, 6, 8	0.94	Accept (Poster)
234	6.67	Analysis Of Quantized Models	6, 7, 7	0.47	Accept (Poster)
235	6.67	Detecting Memorization In Relu Networks	5, 6, 9	1.70	Reject
236	6.67	Snas: Stochastic Neural Architecture Search	6, 7, 7	0.47	Accept (Poster)
237	6.67	Pate-gan: Generating Synthetic Data With Differential Privacy Guarantees	7, 6, 7	0.47	Accept (Poster)
238	6.67	Principled Deep Neural Network Training Through Linear Programming	6, 6, 8	0.94	Reject
239	6.67	Cot: Cooperative Training For Generative Modeling Of Discrete Data	7, 7, 6	0.47	Reject
240	6.67	On The Turing Completeness Of Modern Neural Network Architectures	6, 7, 7	0.47	Accept (Poster)
241	6.67	Layoutgan: Generating Graphic Layouts With Wireframe Discriminators	7, 7, 6	0.47	Accept (Poster)
242	6.67	Learning Factorized Multimodal Representations	7, 7, 6	0.47	Accept (Poster)
243	6.67	Phase-aware Speech Enhancement With Deep Complex U-net	6, 7, 7	0.47	Accept (Poster)
244	6.67	Go Gradient For Expectation-based Objectives	7, 7, 6	0.47	Accept (Poster)
245	6.67	Analyzing Inverse Problems With Invertible Neural Networks	7, 6, 7	0.47	Accept (Poster)
246	6.67	Deep Reinforcement Learning With Relational Inductive Biases	6, 7, 7	0.47	Accept (Poster)
247	6.67	Janossy Pooling: Learning Deep Permutation-invariant Functions For Variable-size Inputs	7, 5, 8	1.25	Accept (Poster)
248	6.67	Improving Generalization And Stability Of Generative Adversarial Networks	7, 7, 6	0.47	Accept (Poster)
249	6.67	Preconditioner On Matrix Lie Group For Sgd	8, 5, 7	1.25	Accept (Poster)
250	6.67	Deep Anomaly Detection With Outlier Exposure	6, 6, 8	0.94	Accept (Poster)
251	6.67	Attention, Learn To Solve Routing Problems!	7, 6, 7	0.47	Accept (Poster)
252	6.67	Learning What And Where To Attend	6, 6, 8	0.94	Accept (Poster)
253	6.67	Query-efficient Hard-label Black-box Attack: An Optimization-based Approach	7, 6, 7	0.47	Accept (Poster)
254	6.67	Recall Traces: Backtracking Models For Efficient Reinforcement Learning	7, 7, 6	0.47	Accept (Poster)
255	6.67	Learning To Infer And Execute 3d Shape Programs	6, 7, 7	0.47	Accept (Poster)
256	6.67	Dom-q-net: Grounded Rl On Structured Language	7, 7, 6	0.47	Accept (Poster)
257	6.67	Toward Understanding The Impact Of Staleness In Distributed Machine Learning	4, 9, 7	2.05	Accept (Poster)
258	6.67	Graph Hypernetworks For Neural Architecture Search	7, 6, 7	0.47	Accept (Poster)
259	6.67	A Generative Model For Electron Paths	8, 4, 8	1.89	Accept (Poster)
260	6.67	Bayesian Prediction Of Future Street Scenes Using Synthetic Likelihoods	6, 8, 6	0.94	Accept (Poster)
261	6.67	Disjoint Mapping Network For Cross-modal Matching Of Voices And Faces	7, 6, 7	0.47	Accept (Poster)
262	6.67	Complement Objective Training	5, 8, 7	1.25	Accept (Poster)
263	6.67	Value Propagation Networks	7, 6, 7	0.47	Accept (Poster)
264	6.67	Trellis Networks For Sequence Modeling	7, 6, 7	0.47	Accept (Poster)
265	6.67	Non-vacuous Generalization Bounds At The Imagenet Scale: A Pac-bayesian Compression Approach	6, 6, 8	0.94	Accept (Poster)
266	6.67	Contingency-aware Exploration In Reinforcement Learning	6, 7, 7	0.47	Accept (Poster)
267	6.67	Context-adaptive Entropy Model For End-to-end Optimized Image Compression	7, 7, 6	0.47	Accept (Poster)
268	6.67	Learning Finite State Representations Of Recurrent Policy Networks	6, 7, 7	0.47	Accept (Poster)
269	6.67	Do Deep Generative Models Know What They Don't Know?	7, 6, 7	0.47	Accept (Poster)
270	6.67	Learning Two-layer Neural Networks With Symmetric Inputs	7, 6, 7	0.47	Accept (Poster)
271	6.67	Minimal Random Code Learning: Getting Bits Back From Compressed Model Parameters	7, 6, 7	0.47	Accept (Poster)
272	6.67	Noodl: Provable Online Dictionary Learning And Sparse Coding	7, 6, 7	0.47	Accept (Poster)
273	6.67	Approximating Cnns With Bag-of-local-features Models Works Surprisingly Well On Imagenet	6, 7, 7	0.47	Accept (Poster)
274	6.67	Understanding Straight-through Estimator In Training Activation Quantized Neural Nets	7, 7, 6	0.47	Accept (Poster)
275	6.67	Antisymmetricrnn: A Dynamical System View On Recurrent Neural Networks	7, 7, 6	0.47	Accept (Poster)
276	6.67	The Limitations Of Adversarial Training And The Blind-spot Attack	7, 7, 6	0.47	Accept (Poster)
277	6.67	A Rotation-equivariant Convolutional Neural Network Model Of Primary Visual Cortex	7, 5, 8	1.25	Accept (Poster)
278	6.67	Generalized Tensor Models For Recurrent Neural Networks	6, 7, 7	0.47	Accept (Poster)
279	6.67	Adversarial Attacks On Graph Neural Networks Via Meta Learning	7, 7, 6	0.47	Accept (Poster)
280	6.67	Training For Faster Adversarial Robustness Verification Via Inducing Relu Stability	8, 7, 5	1.25	Accept (Poster)
281	6.67	Adv-bnn: Improved Adversarial Defense Through Robust Bayesian Neural Network	7, 6, 7	0.47	Accept (Poster)
282	6.67	Initialized Equilibrium Propagation For Backprop-free Training	5, 8, 7	1.25	Accept (Poster)
283	6.67	Learning To Design Rna	6, 6, 8	0.94	Accept (Poster)
284	6.67	Adef: An Iterative Algorithm To Construct Adversarial Deformations	7, 7, 6	0.47	Accept (Poster)
285	6.67	Stable Opponent Shaping In Differentiable Games	8, 6, 6	0.94	Accept (Poster)
286	6.67	Spigan: Privileged Adversarial Learning From Simulation	6, 7, 7	0.47	Accept (Poster)
287	6.67	Metropolis-hastings View On Variational Inference And Adversarial Training	5, 6, 9	1.70	Reject
288	6.67	Beyond Pixel Norm-balls: Parametric Adversaries Using An Analytically Differentiable Renderer	7, 7, 6	0.47	Accept (Poster)
289	6.67	Adaptive Posterior Learning: Few-shot Learning With A Surprise-based Memory Module	6, 7, 7	0.47	Accept (Poster)
290	6.67	Glue: A Multi-task Benchmark And Analysis Platform For Natural Language Understanding	7, 5, 8	1.25	Accept (Poster)
291	6.67	Looking For Elmo's Friends: Sentence-level Pretraining Beyond Language Modeling	5, 7, 8	1.25	Reject
292	6.67	Misgan: Learning From Incomplete Data With Generative Adversarial Networks	7, 6, 7	0.47	Accept (Poster)
293	6.50	Gradient Descent Provably Optimizes Over-parameterized Neural Networks	3, 8, 8, 7	2.06	Accept (Poster)
294	6.50	Relational Forward Models For Multi-agent Learning	7, 6, 7, 6	0.50	Accept (Poster)
295	6.50	Dynamic Channel Pruning: Feature Boosting And Suppression	7, 6, 7, 6	0.50	Accept (Poster)
296	6.50	Learning Protein Structure With A Differentiable Simulator	6, 7, 7, 6	0.50	Accept (Oral)
297	6.50	Preferences Implicit In The State Of The World	6, 7, 6, 7	0.50	Accept (Poster)
298	6.50	Peernets: Exploiting Peer Wisdom Against Adversarial Attacks	7, 6	0.50	Accept (Poster)
299	6.33	Multilingual Neural Machine Translation With Soft Decoupled Encoding	6, 6, 7	0.47	Accept (Poster)
300	6.33	Analysing Mathematical Reasoning Abilities Of Neural Models	7, 6, 6	0.47	Accept (Poster)
301	6.33	Minimum Divergence Vs. Maximum Margin: An Empirical Comparison On Seq2seq Models	5, 7, 7	0.94	Accept (Poster)
302	6.33	Self-tuning Networks: Bilevel Optimization Of Hyperparameters Using Structured Best-response Functions	7, 6, 6	0.47	Accept (Poster)
303	6.33	Learning Disentangled Representations With Reference-based Variational Autoencoders	7, 6, 6	0.47	Reject
304	6.33	Remember And Forget For Experience Replay	7, 6, 6	0.47	Reject
305	6.33	Dpsnet: End-to-end Deep Plane Sweep Stereo	7, 6, 6	0.47	Accept (Poster)
306	6.33	On Tighter Generalization Bounds For Deep Neural Networks: Cnns, Resnets, And Beyond	5, 7, 7	0.94	Reject
307	6.33	Measuring Compositionality In Representation Learning	6, 6, 7	0.47	Accept (Poster)
308	6.33	Reward Constrained Policy Optimization	6, 7, 6	0.47	Accept (Poster)
309	6.33	Regularized Learning For Domain Adaptation Under Label Shifts	7, 6, 6	0.47	Accept (Poster)
310	6.33	A Differentiable Self-disambiguated Sense Embedding Model Via Scaled Gumbel Softmax	7, 6, 6	0.47	Reject
311	6.33	Preventing Posterior Collapse With Delta-vaes	6, 7, 6	0.47	Accept (Poster)
312	6.33	Efficient Augmentation Via Data Subsampling	6, 7, 6	0.47	Accept (Poster)
313	6.33	Double Viterbi: Weight Encoding For High Compression Ratio And Fast On-chip Reconstruction For Deep Neural Network	6, 6, 7	0.47	Accept (Poster)
314	6.33	Rethinking The Value Of Network Pruning	6, 6, 7	0.47	Accept (Poster)
315	6.33	Aligning Artificial Neural Networks To The Brain Yields Shallow Recurrent Architectures	5, 7, 7	0.94	Reject
316	6.33	Equi-normalization Of Neural Networks	7, 7, 5	0.94	Accept (Poster)
317	6.33	Multi-domain Adversarial Learning	5, 8, 6	1.25	Accept (Poster)
318	6.33	Information Theoretic Lower Bounds On Negative Log Likelihood	6, 7, 6	0.47	Accept (Poster)
319	6.33	Dialogwae: Multimodal Response Generation With Conditional Wasserstein Auto-encoder	7, 7, 5	0.94	Accept (Poster)
320	6.33	Monge-amp`ere Flow For Generative Modeling	7, 6, 6	0.47	Reject
321	6.33	Nlprolog: Reasoning With Weak Unification For Natural Language Question Answering	7, 5, 7	0.94	Reject
322	6.33	Attentive Neural Processes	6, 6, 7	0.47	Accept (Poster)
323	6.33	Scalable Unbalanced Optimal Transport Using Generative Adversarial Networks	6, 7, 6	0.47	Accept (Poster)
324	6.33	Structured Neural Summarization	6, 6, 7	0.47	Accept (Poster)
325	6.33	Laplacian Networks: Bounding Indicator Function Smoothness For Neural Networks Robustness	9, 5, 5	1.89	Reject
326	6.33	Accumulation Bit-width Scaling For Ultra-low Precision Training Of Deep Networks	6, 6, 7	0.47	Accept (Poster)
327	6.33	Direct Optimization Through For Discrete Variational Auto-encoder	7, 7, 5	0.94	Reject
328	6.33	Fluctuation-dissipation Relations For Stochastic Gradient Descent	8, 5, 6	1.25	Accept (Poster)
329	6.33	Rnns Implicitly Implement Tensor-product Representations	7, 6, 6	0.47	Accept (Poster)
330	6.33	From Hard To Soft: Understanding Deep Network Nonlinearities Via Vector Quantization And Statistical Inference	6, 6, 7	0.47	Accept (Poster)
331	6.33	Von Mises-fisher Loss For Training Sequence To Sequence Models With Continuous Outputs	6, 7, 6	0.47	Accept (Poster)
332	6.33	Proxylessnas: Direct Neural Architecture Search On Target Task And Hardware	6, 6, 7	0.47	Accept (Poster)
333	6.33	Discriminator Rejection Sampling	7, 6, 6	0.47	Accept (Poster)
334	6.33	Visceral Machines: Risk-aversion In Reinforcement Learning With Intrinsic Physiological Rewards	6, 6, 7	0.47	Accept (Poster)
335	6.33	Fixup Initialization: Residual Learning Without Normalization	7, 5, 7	0.94	Accept (Poster)
336	6.33	Algorithmic Framework For Model-based Deep Reinforcement Learning With Theoretical Guarantees	7, 6, 6	0.47	Accept (Poster)
337	6.33	Understanding Composition Of Word Embeddings Via Tensor Decomposition	7, 6, 6	0.47	Accept (Poster)
338	6.33	Learning To Simulate	6, 6, 7	0.47	Accept (Poster)
339	6.33	Temporal Gaussian Mixture Layer For Videos	6, 6, 7	0.47	Reject
340	6.33	Dher: Hindsight Experience Replay For Dynamic Goals	6, 7, 6	0.47	Accept (Poster)
341	6.33	L2-nonexpansive Neural Networks	8, 6, 5	1.25	Accept (Poster)
342	6.33	Generating Liquid Simulations With Deformation-aware Neural Networks	7, 7, 5	0.94	Accept (Poster)
343	6.33	Camou: Learning Physical Vehicle Camouflages To Adversarially Attack Detectors In The Wild	4, 8, 7	1.70	Accept (Poster)
344	6.33	Timbretron: A Wavenet(cyclegan(cqt(audio))) Pipeline For Musical Timbre Transfer	4, 7, 8	1.70	Accept (Poster)
345	6.33	Synthetic Datasets For Neural Program Synthesis	7, 6, 6	0.47	Accept (Poster)
346	6.33	Delta: Deep Learning Transfer Using Feature Map With Attention For Convolutional Networks	7, 6, 6	0.47	Accept (Poster)
347	6.33	Neural Speed Reading With Structural-jump-lstm	7, 5, 7	0.94	Accept (Poster)
348	6.33	Policy Generalization In Capacity-limited Reinforcement Learning	7, 7, 5	0.94	Reject
349	6.33	Large Scale Graph Learning From Smooth Signals	7, 5, 7	0.94	Accept (Poster)
350	6.33	Post Selection Inference With Incomplete Maximum Mean Discrepancy Estimator	6, 5, 8	1.25	Accept (Poster)
351	6.33	Stable Recurrent Models	7, 6, 6	0.47	Accept (Poster)
352	6.33	On The Relation Between The Sharpest Directions Of Dnn Loss And The Sgd Step Length	6, 6, 7	0.47	Accept (Poster)
353	6.33	Learning To Represent Edits	7, 6, 6	0.47	Accept (Poster)
354	6.33	On Self Modulation For Generative Adversarial Networks	7, 5, 7	0.94	Accept (Poster)
355	6.33	Sgd Converges To Global Minimum In Deep Learning Via Star-convex Path	6, 5, 8	1.25	Accept (Poster)
356	6.33	Neural Graph Evolution: Towards Efficient Automatic Robot Design	5, 8, 6	1.25	Accept (Poster)
357	6.33	The Relativistic Discriminator: A Key Element Missing From Standard Gan	6, 6, 7	0.47	Accept (Poster)
358	6.33	Augmented Cyclic Adversarial Learning For Low Resource Domain Adaptation	8, 6, 5	1.25	Accept (Poster)
359	6.33	Seq2slate: Re-ranking And Slate Optimization With Rnns	6, 6, 7	0.47	Reject
360	6.33	A Novel Variational Family For Hidden Non-linear Markov Models	5, 8, 6	1.25	Reject
361	6.33	Hierarchical Visuomotor Control Of Humanoids	5, 8, 6	1.25	Accept (Poster)
362	6.33	Single Shot Neural Architecture Search Via Direct Sparse Optimization	6, 6, 7	0.47	Reject
363	6.33	Beyond Greedy Ranking: Slate Optimization Via List-cvae	6, 6, 7	0.47	Accept (Poster)
364	6.33	Local Critic Training Of Deep Neural Networks	6, 6, 7	0.47	Reject
365	6.33	On The Sensitivity Of Adversarial Robustness To Input Data Distributions	7, 5, 7	0.94	Accept (Poster)
366	6.33	A Rotation And A Translation Suffice: Fooling Cnns With Simple Transformations	8, 6, 5	1.25	Reject
367	6.33	Verification Of Non-linear Specifications For Neural Networks	7, 5, 7	0.94	Accept (Poster)
368	6.33	Visual Reasoning By Progressive Module Networks	6, 7, 6	0.47	Accept (Poster)
369	6.33	Hierarchical Interpretations For Neural Network Predictions	7, 6, 6	0.47	Accept (Poster)
370	6.33	Robust Estimation Via Generative Adversarial Networks	7, 5, 7	0.94	Accept (Poster)
371	6.33	Large-scale Answerer In Questioner's Mind For Visual Dialog Question Generation	6, 6, 7	0.47	Accept (Poster)
372	6.33	Stochastic Gradient Descent Learns State Equations With Nonlinear Activations	7, 5, 7	0.94	Reject
373	6.33	Selfless Sequential Learning	7, 6, 6	0.47	Accept (Poster)
374	6.33	Mae: Mutual Posterior-divergence Regularization For Variational Autoencoders	7, 6, 6	0.47	Accept (Poster)
375	6.33	Information Asymmetry In Kl-regularized Rl	7, 5, 7	0.94	Accept (Poster)
376	6.33	Poincare Glove: Hyperbolic Word Embeddings	6, 6, 7	0.47	Accept (Poster)
377	6.33	From Language To Goals: Inverse Reinforcement Learning For Vision-based Instruction Following	5, 5, 9	1.89	Accept (Poster)
378	6.33	Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method For Image Restoration	6, 6, 7	0.47	Accept (Poster)
379	6.33	Soft Q-learning With Mutual-information Regularization	7, 6, 6	0.47	Accept (Poster)
380	6.33	M^3rl: Mind-aware Multi-agent Management Reinforcement Learning	7, 6, 6	0.47	Accept (Poster)
381	6.33	Invariance And Inverse Stability Under Relu	6, 6, 7	0.47	Reject
382	6.33	Diversity And Depth In Per-example Routing Models	7, 6, 6	0.47	Accept (Poster)
383	6.33	Revealing Interpretable Object Representations From Human Behavior	7, 7, 5	0.94	Accept (Poster)
384	6.33	Learning Factorized Representations For Open-set Domain Adaptation	6, 6, 7	0.47	Accept (Poster)
385	6.33	Functional Variational Bayesian Neural Networks	7, 6, 6	0.47	Accept (Poster)
386	6.33	Emi: Exploration With Mutual Information Maximizing State And Action Embeddings	5, 7, 7	0.94	Reject
387	6.33	Modeling The Long Term Future In Model-based Reinforcement Learning	6, 6, 7	0.47	Accept (Poster)
388	6.33	Deepobs: A Deep Learning Optimizer Benchmark Suite	6, 6, 7	0.47	Accept (Poster)
389	6.33	Empirical Bounds On Linear Regions Of Deep Rectifier Networks	6, 7, 6	0.47	Reject
390	6.33	Signsgd With Majority Vote Is Communication Efficient And Fault Tolerant	6, 6, 7	0.47	Accept (Poster)
391	6.33	Babyai: A Platform To Study The Sample Efficiency Of Grounded Language Learning	6, 7, 6	0.47	Accept (Poster)
392	6.33	Excessive Invariance Causes Adversarial Vulnerability	7, 6, 6	0.47	Accept (Poster)
393	6.33	Overcoming The Disentanglement Vs Reconstruction Trade-off Via Jacobian Supervision	7, 7, 5	0.94	Accept (Poster)
394	6.33	Feature-wise Bias Amplification	6, 7, 6	0.47	Accept (Poster)
395	6.33	Why Do Deep Convolutional Networks Generalize So Poorly To Small Image Transformations?	7, 7, 5	0.94	Reject
396	6.33	Hierarchical Generative Modeling For Controllable Speech Synthesis	8, 6, 5	1.25	Accept (Poster)
397	6.33	Multi-step Retriever-reader Interaction For Scalable Open-domain Question Answering	6, 6, 7	0.47	Accept (Poster)
398	6.33	Improved Gradient Estimators For Stochastic Discrete Variables	7, 6, 6	0.47	Reject
399	6.33	Characterizing Audio Adversarial Examples Using Temporal Dependency	6, 6, 7	0.47	Accept (Poster)
400	6.33	Data-dependent Coresets For Compressing Neural Networks With Applications To Generalization Bounds	6, 7, 6	0.47	Accept (Poster)
401	6.33	Meta-learning With Latent Embedding Optimization	6, 5, 8	1.25	Accept (Poster)
402	6.33	Probabilistic Planning With Sequential Monte Carlo Methods	8, 6, 5	1.25	Accept (Poster)
403	6.33	Learning What You Can Do Before Doing Anything	7, 6, 6	0.47	Accept (Poster)
404	6.33	Model-predictive Policy Learning With Uncertainty Regularization For Driving In Dense Traffic	6, 6, 7	0.47	Accept (Poster)
405	6.33	Spreading Vectors For Similarity Search	6, 7, 6	0.47	Accept (Poster)
406	6.33	Learning When To Communicate At Scale In Multiagent Cooperative And Competitive Tasks	7, 6, 6	0.47	Accept (Poster)
407	6.33	Opportunistic Learning: Budgeted Cost-sensitive Learning From Data Streams	6, 6, 7	0.47	Accept (Poster)
408	6.33	The Singular Values Of Convolutional Layers	8, 4, 7	1.70	Accept (Poster)
409	6.33	Exemplar Guided Unsupervised Image-to-image Translation With Semantic Consistency	6, 5, 8	1.25	Accept (Poster)
410	6.33	Learning-based Frequency Estimation Algorithms	7, 6, 6	0.47	Accept (Poster)
411	6.33	Max-mig: An Information Theoretic Approach For Joint Learning From Crowds	6, 6, 7	0.47	Accept (Poster)
412	6.33	Multiple-attribute Text Rewriting	7, 6, 6	0.47	Accept (Poster)
413	6.33	Harmonizing Maximum Likelihood With Gans For Multimodal Conditional Generation	8, 7, 4	1.70	Accept (Poster)
414	6.33	Variational Autoencoder With Arbitrary Conditioning	7, 6, 6	0.47	Accept (Poster)
415	6.33	A New Dog Learns Old Tricks: Rl Finds Classic Optimization Algorithms	6, 6, 7	0.47	Accept (Poster)
416	6.33	Generating Multi-agent Trajectories Using Programmatic Weak Supervision	7, 6, 6	0.47	Accept (Poster)
417	6.25	Maximal Divergence Sequential Autoencoder For Binary Software Vulnerability Detection	6, 7, 6, 6	0.43	Accept (Poster)
418	6.25	Neural Tts Stylization With Adversarial And Collaborative Games	6, 6, 6, 7	0.43	Accept (Poster)
419	6.25	Competitive Experience Replay	5, 7, 6, 7	0.83	Accept (Poster)
420	6.25	Bayesian Policy Optimization For Model Uncertainty	5, 6, 7, 7	0.83	Accept (Poster)
421	6.25	Sinkhorn Autoencoders	5, 6, 7, 7	0.83	Reject
422	6.25	Two-timescale Networks For Nonlinear Value Function Approximation	6, 7, 6, 6	0.43	Accept (Poster)
423	6.25	Lyapunov-based Safe Policy Optimization	6, 6, 8, 5	1.09	Reject
424	6.25	Towards Consistent Performance On Atari Using Expert Demonstrations	6, 5, 7, 7	0.83	Reject
425	6.00	Learning Implicit Generative Models By Teaching Explicit Ones	7, 5, 6	0.82	Reject
426	6.00	Emerging Disentanglement In Auto-encoder Based Unsupervised Image Content Transfer	6, 6, 6	0.00	Accept (Poster)
427	6.00	Projective Subspace Networks For Few-shot Learning	6, 6, 6	0.00	Reject
428	6.00	Environment Probing Interaction Policies	6, 6, 6	0.00	Accept (Poster)
429	6.00	Stcn: Stochastic Temporal Convolutional Networks	6, 6, 6	0.00	Accept (Poster)
430	6.00	Capsule Graph Neural Network	6, 6, 6	0.00	Accept (Poster)
431	6.00	Top-down Neural Model For Formulae	6, 6, 6	0.00	Accept (Poster)
432	6.00	Tarmac: Targeted Multi-agent Communication	6, 6, 6	0.00	Reject
433	6.00	Coarse-grain Fine-grain Coattention Network For Multi-evidence Question Answering	7, 7, 4	1.41	Accept (Poster)
434	6.00	Learning Programmatically Structured Representations With Perceptor Gradients	7, 6, 5	0.82	Accept (Poster)
435	6.00	Graph Transformer	6, 6, 6	0.00	Reject
436	6.00	Feed-forward Propagation In Probabilistic Neural Networks With Categorical And Max Layers	6, 6, 6	0.00	Accept (Poster)
437	6.00	Discriminative Active Learning	8, 6, 4	1.63	Reject
438	6.00	Neural Logic Machines	6, 7, 5	0.82	Accept (Poster)
439	6.00	Improving Sequence-to-sequence Learning Via Optimal Transport	6, 7, 5	0.82	Accept (Poster)
440	6.00	Backpropamine: Training Self-modifying Neural Networks With Differentiable Neuromodulated Plasticity	4, 9, 5	2.16	Accept (Poster)
441	6.00	Learning To Propagate Labels: Transductive Propagation Network For Few-shot Learning	5, 6, 7	0.82	Accept (Poster)
442	6.00	Neural Mmo: A Massively Multiplayer Game Environment For Intelligent Agents	6, 5, 7	0.82	Reject
443	6.00	Learnable Embedding Space For Efficient Neural Architecture Compression	5, 7, 6	0.82	Accept (Poster)
444	6.00	Ib-gan: Disentangled Representation Learning With Information Bottleneck Gan	7, 7, 4	1.41	Reject
445	6.00	Interpolation-prediction Networks For Irregularly Sampled Time Series	6, 6, 6	0.00	Accept (Poster)
446	6.00	Learning Models For Visual 3d Localization With Implicit Mapping	7, 5, 6	0.82	Reject
447	6.00	Transfer Learning For Related Reinforcement Learning Tasks Via Image-to-image Translation	7, 7, 4	1.41	Reject
448	6.00	Countering Language Drift Via Grounding	6, 6, 6	0.00	Reject
449	6.00	H-detach: Modifying The Lstm Gradient Towards Better Optimization	5, 6, 7	0.82	Accept (Poster)
450	6.00	Rigorous Agent Evaluation: An Adversarial Approach To Uncover Catastrophic Failures	6, 6, 6	0.00	Accept (Poster)
451	6.00	Multi-class Classification Without Multi-class Labels	6, 7, 5	0.82	Accept (Poster)
452	6.00	Dadam: A Consensus-based Distributed Adaptive Gradient Method For Online Optimization	8, 4, 6	1.63	Reject
453	6.00	A Biologically Inspired Visual Working Memory For Deep Networks	4, 5, 9	2.16	Reject
454	6.00	Multi-agent Dual Learning	6, 6, 6	0.00	Accept (Poster)
455	6.00	Dirichlet Variational Autoencoder	6, 5, 7	0.82	Reject
456	6.00	Graph Convolutional Network With Sequential Attention For Goal-oriented Dialogue Systems	5, 6, 7	0.82	Reject
457	6.00	Unsupervised Neural Multi-document Abstractive Summarization Of Reviews	5, 4, 9	2.16	Reject
458	6.00	Semi-supervised Learning With Multi-domain Sentiment Word Embeddings	6, 6, 6	0.00	Reject
459	6.00	Guiding Policies With Language Via Meta-learning	6, 6, 6	0.00	Accept (Poster)
460	6.00	Improving Sentence Representations With Multi-view Frameworks	7, 6, 5	0.82	Reject
461	6.00	Estimating Information Flow In Dnns	7, 7, 4	1.41	Reject
462	6.00	Identifying Bias In Ai Using Simulation	5, 7, 6	0.82	Reject
463	6.00	Graph Wavelet Neural Network	4, 7, 7	1.41	Accept (Poster)
464	6.00	Recurrent Kalman Networks: Factorized Inference In High-dimensional Deep Feature Spaces	6, 6, 6	0.00	Reject
465	6.00	Learning Procedural Abstractions And Evaluating Discrete Latent Temporal Structure	6, 5, 7	0.82	Accept (Poster)
466	6.00	Adversarial Information Factorization	6, 6, 6	0.00	Reject
467	6.00	Bnn+: Improved Binary Network Training	8, 6, 4	1.63	Reject
468	6.00	An Empirical Study Of Binary Neural Networks' Optimisation	8, 6, 4	1.63	Accept (Poster)
469	6.00	Graph U-net	7, 4, 7	1.41	Reject
470	6.00	Distribution-interpolation Trade Off In Generative Models	6, 7, 5	0.82	Accept (Poster)
471	6.00	A Closer Look At Few-shot Classification	6, 6, 6	0.00	Accept (Poster)
472	6.00	Decoupled Weight Decay Regularization	6, 7, 5	0.82	Accept (Poster)
473	6.00	An Adaptive Homeostatic Algorithm For The Unsupervised Learning Of Visual Features	5, 4, 9	2.16	Reject
474	6.00	Efficient Two-step Adversarial Defense For Deep Neural Networks	5, 6, 7	0.82	Reject
475	6.00	Cramer-wold Autoencoder	5, 7, 6	0.82	Reject
476	6.00	Precision Highway For Ultra Low-precision Quantization	6, 7, 5	0.82	Reject
477	6.00	Graphseq2seq: Graph-sequence-to-sequence For Neural Machine Translation	6, 6, 6	0.00	Reject
478	6.00	Learning Multi-level Hierarchies With Hindsight	6, 7, 5	0.82	Accept (Poster)
479	6.00	The Variational Deficiency Bottleneck	5, 7, 6	0.82	Reject
480	6.00	Universal Successor Features Approximators	7, 5, 6	0.82	Accept (Poster)
481	6.00	Deep Lagrangian Networks: Using Physics As Model Prior For Deep Learning	7, 4, 7	1.41	Accept (Poster)
482	6.00	Neural Program Repair By Jointly Learning To Localize And Repair	6, 7, 5	0.82	Accept (Poster)
483	6.00	Measuring And Regularizing Networks In Function Space	6, 6, 6	0.00	Accept (Poster)
484	6.00	Anytime Minibatch: Exploiting Stragglers In Online Distributed Optimization	4, 7, 7	1.41	Accept (Poster)
485	6.00	Stochastic Gradient Push For Distributed Deep Learning	6, 6, 6	0.00	Reject
486	6.00	A Direct Approach To Robust Deep Learning Using Adversarial Networks	5, 7, 6	0.82	Accept (Poster)
487	6.00	Gamepad: A Learning Environment For Theorem Proving	4, 7, 7	1.41	Accept (Poster)
488	6.00	Don’t Judge A Book By Its Cover - On The Dynamics Of Recurrent Neural Networks	5, 7, 6	0.82	Reject
489	6.00	Uncovering Surprising Behaviors In Reinforcement Learning Via Worst-case Analysis	5, 7, 6	0.82	Reject
490	6.00	Language Model Pre-training For Hierarchical Document Representations	6, 6, 6	0.00	Reject
491	6.00	Manifold Mixup: Learning Better Representations By Interpolating Hidden States	6, 4, 8	1.63	Reject
492	6.00	Dimension-free Bounds For Low-precision Training	6, 6, 6	0.00	Reject
493	6.00	Kernel Rnn Learning (kernl)	5, 7, 6	0.82	Accept (Poster)
494	6.00	Datnet: Dual Adversarial Transfer For Low-resource Named Entity Recognition	6, 6, 6	0.00	Reject
495	6.00	Optimistic Mirror Descent In Saddle-point Problems: Going The Extra (gradient) Mile	7, 6, 5	0.82	Accept (Poster)
496	6.00	Deep Convolutional Networks As Shallow Gaussian Processes	5, 8, 5	1.41	Accept (Poster)
497	6.00	On The Computational Inefficiency Of Large Batch Sizes For Stochastic Gradient Descent	5, 8, 5	1.41	Reject
498	6.00	Wasserstein Barycenter Model Ensembling	6, 6, 6	0.00	Accept (Poster)
499	6.00	Computing Committor Functions For The Study Of Rare Events Using Deep Learning With Importance Sampling	6, 6, 5, 7	0.71	Reject
500	6.00	Scaling Shared Model Governance Via Model Splitting	4, 5, 9	2.16	Reject
501	6.00	Generative Feature Matching Networks	6, 6, 6, 6	0.00	Reject
502	6.00	Mixed Precision Quantization Of Convnets Via Differentiable Neural Architecture Search	5, 6, 7, 6	0.71	Reject
503	6.00	Alignment Based Mathching Networks For One-shot Classification And Open-set Recognition	7, 6, 7, 4	1.22	Reject
504	6.00	Unsupervised Adversarial Image Reconstruction	6, 8, 4	1.63	Accept (Poster)
505	6.00	Adversarial Reprogramming Of Neural Networks	4, 6, 8	1.63	Accept (Poster)
506	6.00	Reinforcement Learning With Perturbed Rewards	6, 6, 6	0.00	Reject
507	6.00	Variational Bayesian Phylogenetic Inference	6, 5, 7	0.82	Accept (Poster)
508	6.00	Efficient Multi-objective Neural Architecture Search Via Lamarckian Evolution	6, 6, 6	0.00	Accept (Poster)
509	6.00	On-policy Trust Region Policy Optimisation With Replay Buffers	7, 6, 5	0.82	Reject
510	6.00	A Max-affine Spline Perspective Of Recurrent Neural Networks	6, 6, 6	0.00	Accept (Poster)
511	6.00	Explicit Information Placement On Latent Variables Using Auxiliary Generative Modelling Task	6, 7, 5	0.82	Reject
512	6.00	Code2seq: Generating Sequences From Structured Representations Of Code	6, 7, 5	0.82	Accept (Poster)
513	6.00	Overcoming Catastrophic Forgetting For Continual Learning Via Model Adaptation	5, 6, 7	0.82	Accept (Poster)
514	6.00	Dl2: Training And Querying Neural Networks With Logic	7, 5, 6	0.82	Reject
515	6.00	Cost-sensitive Robustness Against Adversarial Examples	5, 5, 8	1.41	Accept (Poster)
516	6.00	Robust Conditional Generative Adversarial Networks	6, 6, 6	0.00	Accept (Poster)
517	6.00	Unsupervised Discovery Of Parts, Structure, And Dynamics	6, 6, 7, 5	0.71	Accept (Poster)
518	6.00	Learning To Learn With Conditional Class Dependencies	6, 8, 4	1.63	Accept (Poster)
519	6.00	Aggregated Momentum: Stability Through Passive Damping	7, 6, 5	0.82	Accept (Poster)
520	6.00	Discovery Of Natural Language Concepts In Individual Units Of Cnns	6, 6, 6	0.00	Accept (Poster)
521	6.00	Generative Predecessor Models For Sample-efficient Imitation Learning	6, 5, 7	0.82	Accept (Poster)
522	6.00	Image Deformation Meta-network For One-shot Learning	5, 7, 6	0.82	N/A
523	6.00	Adversarial Vulnerability Of Neural Networks Increases With Input Dimension	6, 4, 9, 5	1.87	Reject
524	6.00	How To Train Your Maml	5, 6, 7	0.82	Accept (Poster)
525	6.00	Learning Kolmogorov Models For Binary Random Variables	5, 5, 8	1.41	Reject
526	6.00	Unsupervised Hyper-alignment For Multilingual Word Embeddings	5, 6, 7	0.82	Accept (Poster)
527	6.00	Adversarial Imitation Via Variational Inverse Reinforcement Learning	6, 6, 6	0.00	Accept (Poster)
528	6.00	Improving The Generalization Of Adversarial Training With Domain Adaptation	6, 6, 6	0.00	Accept (Poster)
529	6.00	Formal Limitations On The Measurement Of Mutual Information	8, 6, 4	1.63	Reject
530	6.00	Online Hyperparameter Adaptation Via Amortized Proximal Optimization	6, 5, 7	0.82	Reject
531	6.00	Machine Translation With Weakly Paired Bilingual Documents	6, 5, 7	0.82	Reject
532	6.00	Greedy Attack And Gumbel Attack: Generating Adversarial Examples For Discrete Data	3, 6, 8, 7	1.87	Reject
533	6.00	Variance Networks: When Expectation Does Not Meet Your Expectations	6, 6, 6	0.00	Accept (Poster)
534	6.00	Shallow Learning For Deep Networks	6, 5, 7	0.82	Reject
535	6.00	Success At Any Cost: Value Constrained Model-free Continuous Control	7, 5, 6	0.82	Reject
536	6.00	Language Modeling Teaches You More Syntax Than Translation Does: Lessons Learned Through Auxiliary Task Analysis	6, 5, 7	0.82	Reject
537	6.00	Hierarchical Reinforcement Learning Via Advantage-weighted Information Maximization	5, 6, 7	0.82	Accept (Poster)
538	6.00	Mean-field Analysis Of Batch Normalization	7, 6, 5	0.82	Reject
539	6.00	Learning From Positive And Unlabeled Data With A Selection Bias	7, 6, 5	0.82	Accept (Poster)
540	6.00	A Kernel Random Matrix-based Approach For Sparse Pca	5, 7, 6	0.82	Accept (Poster)
541	6.00	Per-tensor Fixed-point Quantization Of The Back-propagation Algorithm	7, 3, 8	2.16	Accept (Poster)
542	6.00	Fortified Networks: Improving The Robustness Of Deep Networks By Modeling The Manifold Of Hidden Representations	4, 5, 9, 6	1.87	Reject
543	6.00	A Comprehensive, Application-oriented Study Of Catastrophic Forgetting In Dnns	5, 6, 7	0.82	Accept (Poster)
544	6.00	Interactive Agent Modeling By Learning To Probe	6, 6, 6, 6	0.00	Reject
545	6.00	Learning Heuristics For Automated Reasoning Through Reinforcement Learning	5, 6, 7	0.82	Reject
546	6.00	Stochastic Prediction Of Multi-agent Interactions From Partial Observations	6, 6, 6	0.00	Accept (Poster)
547	6.00	Combinatorial Attacks On Binarized Neural Networks	5, 6, 7	0.82	Accept (Poster)
548	6.00	Invase: Instance-wise Variable Selection Using Neural Networks	6, 6, 6	0.00	Accept (Poster)
549	5.75	On The Margin Theory Of Feedforward Neural Networks	5, 5, 6, 7	0.83	Reject
550	5.75	Neural Networks For Modeling Source Code Edits	5, 6, 6, 6	0.43	Reject
551	5.75	Efficiently Testing Local Optimality And Escaping Saddles For Relu Networks	3, 6, 6, 8	1.79	Accept (Poster)
552	5.75	Automata Guided Skill Composition	7, 5, 6, 5	0.83	Reject
553	5.67	A More Globally Accurate Dimensionality Reduction Method Using Triplets	6, 5, 6	0.47	Reject
554	5.67	Eddi: Efficient Dynamic Discovery Of High-value Information With Partial Vae	6, 5, 6	0.47	Reject
555	5.67	Deep Imitative Models For Flexible Inference, Planning, And Control	5, 6, 6	0.47	Reject
556	5.67	Set Transformer	5, 6, 6	0.47	Reject
557	5.67	Transfer Learning Via Unsupervised Task Discovery For Visual Question Answering	4, 5, 8	1.70	N/A
558	5.67	Information Regularized Neural Networks	6, 6, 5	0.47	Reject
559	5.67	An Information-theoretic Metric Of Transferability For Task Transfer Learning	5, 6, 6	0.47	Reject
560	5.67	Detecting Out-of-distribution Samples Using Low-order Deep Features Statistics	5, 5, 7	0.94	Reject
561	5.67	Laplacian Smoothing Gradient Descent	6, 6, 5	0.47	Reject
562	5.67	Cross-task Knowledge Transfer For Visually-grounded Navigation	7, 5, 5	0.94	Reject
563	5.67	Super-resolution Via Conditional Implicit Maximum Likelihood Estimation	5, 6, 6	0.47	Reject
564	5.67	Mode Normalization	5, 6, 6	0.47	Accept (Poster)
565	5.67	Learning Cross-lingual Sentence Representations Via A Multi-task Dual-encoder Model	7, 4, 6	1.25	Reject
566	5.67	Ppo-cma: Proximal Policy Optimization With Covariance Matrix Adaptation	4, 9, 4	2.36	Reject
567	5.67	A Resizable Mini-batch Gradient Descent Based On A Multi-armed Bandit	6, 7, 4	1.25	Reject
568	5.67	Understanding Gans Via Generalization Analysis For Disconnected Support	6, 5, 6	0.47	Reject
569	5.67	Open-ended Content-style Recombination Via Leakage Filtering	7, 5, 5	0.94	Reject
570	5.67	Adversarial Audio Synthesis	5, 6, 6	0.47	Accept (Poster)
571	5.67	A Variational Dirichlet Framework For Out-of-distribution Detection	6, 5, 6	0.47	Reject
572	5.67	Stochastic Adversarial Video Prediction	6, 6, 5	0.47	Reject
573	5.67	Transfer Learning For Sequences Via Learning To Collocate	6, 5, 6	0.47	Accept (Poster)
574	5.67	Talk The Walk: Navigating Grids In New York City Through Grounded Dialogue	6, 7, 4	1.25	Reject
575	5.67	Random Mesh Projectors For Inverse Problems	6, 7, 4	1.25	Accept (Poster)
576	5.67	Infobot: Transfer And Exploration Via The Information Bottleneck	7, 7, 3	1.89	Accept (Poster)
577	5.67	Trace-back Along Capsules And Its Application On Semantic Segmentation	6, 6, 5	0.47	Reject
578	5.67	Adversarially Learned Mixture Model	6, 5, 6	0.47	Reject
579	5.67	Unsupervised Document Representation Using Partition Word-vectors Averaging	6, 7, 4	1.25	Reject
580	5.67	Deep Recurrent Gaussian Process With Variational Sparse Spectrum Approximation	5, 5, 7	0.94	Reject
581	5.67	A Frank-wolfe Framework For Efficient And Effective Adversarial Attacks	5, 5, 7	0.94	Reject
582	5.67	Adaptive Gradient Methods With Dynamic Bound Of Learning Rate	7, 4, 6	1.25	Accept (Poster)
583	5.67	Convolutional Crfs For Semantic Segmentation	7, 4, 6	1.25	Reject
584	5.67	Ppd: Permutation Phase Defense Against Adversarial Examples In Deep Learning	6, 7, 4	1.25	Reject
585	5.67	Generalizable Adversarial Training Via Spectral Normalization	6, 5, 6	0.47	Accept (Poster)
586	5.67	Cbow Is Not All You Need: Combining Cbow With The Compositional Matrix Space Model	6, 5, 6	0.47	Accept (Poster)
587	5.67	Soseleto: A Unified Approach To Transfer Learning And Training With Noisy Labels	7, 5, 5	0.94	Reject
588	5.67	Revisiting Reweighted Wake-sleep	5, 6, 6	0.47	Reject
589	5.67	Lipschitz Regularized Deep Neural Networks Generalize	4, 6, 7	1.25	Reject
590	5.67	Necst: Neural Joint Source-channel Coding	6, 4, 7	1.25	Reject
591	5.67	Multi-objective Training Of Generative Adversarial Networks With Multiple Discriminators	6, 5, 6	0.47	Reject
592	5.67	Small Steps And Giant Leaps: Minimal Newton Solvers For Deep Learning	7, 7, 3	1.89	Reject
593	5.67	Actrce: Augmenting Experience Via Teacher’s Advice	5, 7, 5	0.94	Reject
594	5.67	Adaptive Sample-space & Adaptive Probability Coding: A Neural-network Based Approach For Compression	5, 7, 5	0.94	Reject
595	5.67	Collapse Of Deep And Narrow Neural Nets	6, 4, 7	1.25	Reject
596	5.67	Incremental Training Of Multi-generative Adversarial Networks	5, 6, 6	0.47	Reject
597	5.67	Visual Explanation By Interpretation: Improving Visual Feedback Capabilities Of Deep Neural Networks	8, 4, 5	1.70	Accept (Poster)
598	5.67	The Loss Landscape Of Overparameterized Neural Networks	5, 7, 5	0.94	Reject
599	5.67	Rotation Equivariant Networks Via Conic Convolution And The Dft	4, 7, 6	1.25	N/A
600	5.67	Backprop With Approximate Activations For Memory-efficient Network Training	5, 7, 5	0.94	Reject
601	5.67	Nested Dithered Quantization For Communication Reduction In Distributed Training	5, 5, 7	0.94	Reject
602	5.67	Switching Linear Dynamics For Variational Bayes Filtering	6, 4, 7	1.25	Reject
603	5.67	Exploring The Interpretability Of Lstm Neural Networks Over Multi-variable Data	6, 5, 6	0.47	Reject
604	5.67	Pix2scene: Learning Implicit 3d Representations From Images	5, 6, 6	0.47	Reject
605	5.67	Manifold Regularization With Gans For Semi-supervised Learning	7, 5, 5	0.94	Reject
606	5.67	Random Mask: Towards Robust Convolutional Neural Networks	6, 7, 4	1.25	Reject
607	5.67	Predict Then Propagate: Graph Neural Networks Meet Personalized Pagerank	5, 5, 7	0.94	Accept (Poster)
608	5.67	Pyramid Recurrent Neural Networks For Multi-scale Change-point Detection	4, 6, 7	1.25	Reject
609	5.67	Adversarial Attacks On Node Embeddings	5, 6, 6	0.47	Reject
610	5.67	Learning Exploration Policies For Navigation	3, 7, 7	1.89	Accept (Poster)
611	5.67	Domain Adaptation For Structured Output Via Disentangled Patch Representations	7, 5, 5	0.94	Reject
612	5.67	Doubly Sparse: Sparse Mixture Of Sparse Experts For Efficient Softmax Inference	6, 4, 7	1.25	Reject
613	5.67	Infinitely Deep Infinite-width Networks	5, 6, 6	0.47	Reject
614	5.67	A Model Cortical Network For Spatiotemporal Sequence Learning And Prediction	7, 7, 3	1.89	Reject
615	5.67	Perception-aware Point-based Value Iteration For Partially Observable Markov Decision Processes	6, 4, 7	1.25	Reject
616	5.67	Adversarial Exploration Strategy For Self-supervised Imitation Learning	7, 5, 5	0.94	Reject
617	5.67	Gradient-based Training Of Slow Feature Analysis By Differentiable Approximate Whitening	5, 6, 6	0.47	Reject
618	5.67	A Closer Look At Deep Learning Heuristics: Learning Rate Restarts, Warmup And Distillation	4, 7, 6	1.25	Accept (Poster)
619	5.67	Learning State Representations In Complex Systems With Multimodal Data	6, 6, 5	0.47	Reject
620	5.67	Representing Formal Languages: A Comparison Between Finite Automata And Recurrent Neural Networks	7, 5, 5	0.94	Accept (Poster)
621	5.67	Controlling Covariate Shift Using Equilibrium Normalization Of Weights	4, 6, 7	1.25	Reject
622	5.67	Accelerating Nonconvex Learning Via Replica Exchange Langevin Diffusion	4, 7, 6	1.25	Accept (Poster)
623	5.67	Neural Networks With Structural Resistance To Adversarial Attacks	5, 5, 7	0.94	Reject
624	5.67	Interactive Parallel Exploration For Reinforcement Learning In Continuous Action Spaces	6, 4, 7	1.25	Reject
625	5.67	Neural Separation Of Observed And Unobserved Distributions	6, 5, 6	0.47	Reject
626	5.67	Dynamic Early Terminating Of Multiply Accumulate Operations For Saving Computation Cost In Convolutional Neural Networks	5, 6, 6	0.47	Reject
627	5.67	Codraw: Collaborative Drawing As A Testbed For Grounded Goal-driven Communication	4, 6, 7	1.25	Reject
628	5.67	Understanding & Generalizing Alphago Zero	5, 7, 5	0.94	Reject
629	5.67	Learning Actionable Representations With Goal Conditioned Policies	5, 6, 6	0.47	Accept (Poster)
630	5.67	Deep Denoising: Rate-optimal Recovery Of Structured Signals With A Deep Prior	6, 5, 6	0.47	Reject
631	5.67	Attentive Task-agnostic Meta-learning For Few-shot Text Classification	5, 5, 7	0.94	Reject
632	5.67	Mile: A Multi-level Framework For Scalable Graph Embedding	7, 4, 6	1.25	Reject
633	5.67	Stochastic Gradient/mirror Descent: Minimax Optimality And Implicit Regularization	7, 5, 5	0.94	Accept (Poster)
634	5.67	Teacher Guided Architecture Search	6, 5, 6	0.47	Reject
635	5.67	Knowledge Representation For Reinforcement Learning Using General Value Functions	6, 7, 4	1.25	N/A
636	5.67	Learning Neural Random Fields With Inclusive Auxiliary Generators	6, 6, 5	0.47	Reject
637	5.67	Lit: Block-wise Intermediate Representation Training For Model Compression	5, 6, 6	0.47	Reject
638	5.67	Adaptive Mixture Of Low-rank Factorizations For Compact Neural Modeling	4, 6, 7	1.25	Reject
639	5.67	Learning Backpropagation-free Deep Architectures With Kernels	6, 6, 5	0.47	Reject
640	5.67	Identifying Generalization Properties In Neural Networks	6, 5, 6	0.47	Reject
641	5.67	Unsupervised Learning Of Sentence Representations Using Sequence Consistency	7, 5, 5	0.94	Reject
642	5.67	Dana: Scalable Out-of-the-box Distributed Asgd Without Retuning	5, 7, 5	0.94	Reject
643	5.67	Clean-label Backdoor Attacks	6, 7, 4	1.25	Reject
644	5.67	Meta-learning With Domain Adaptation For Few-shot Learning Under Domain Shift	6, 5, 6	0.47	Reject
645	5.67	Amortized Bayesian Meta-learning	6, 5, 6	0.47	Accept (Poster)
646	5.67	(unconstrained) Beam Search Is Sensitive To Large Search Discrepancies	5, 5, 7	0.94	Reject
647	5.67	Universal Successor Features For Transfer Reinforcement Learning	4, 7, 6	1.25	Reject
648	5.67	Learning Embeddings Into Entropic Wasserstein Spaces	7, 7, 3	1.89	Accept (Poster)
649	5.67	Reliable Uncertainty Estimates In Deep Neural Networks Using Noise Contrastive Priors	7, 4, 6	1.25	Reject
650	5.67	Can I Trust You More? Model-agnostic Hierarchical Explanations	6, 6, 5	0.47	Reject
651	5.67	Hallucinations In Neural Machine Translation	6, 4, 7	1.25	Reject
652	5.67	Learning Data-derived Privacy Preserving Representations From Information Metrics	6, 5, 6	0.47	Reject
653	5.67	The Expressive Power Of Deep Neural Networks With Circulant Matrices	4, 7, 6	1.25	Reject
654	5.67	Flow++: Improving Flow-based Generative Models With Variational Dequantization And Architecture Design	6, 6, 5	0.47	Reject
655	5.67	Overcoming Multi-model Forgetting	6, 5, 6	0.47	Reject
656	5.67	Graph Matching Networks For Learning The Similarity Of Graph Structured Objects	5, 6, 6	0.47	Reject
657	5.67	Aim: Adversarial Inference By Matching Priors And Conditionals	7, 4, 6	1.25	Reject
658	5.67	Where Off-policy Deep Reinforcement Learning Fails	7, 5, 5	0.94	Reject
659	5.67	Explaining Image Classifiers By Counterfactual Generation	5, 7, 5	0.94	Accept (Poster)
660	5.67	Adaptive Network Sparsification Via Dependent Variational Beta-bernoulli Dropout	5, 5, 7	0.94	Reject
661	5.67	Unsupervised Emergence Of Spatial Structure From Sensorimotor Prediction	4, 6, 7	1.25	Reject
662	5.67	State-regularized Recurrent Networks	6, 6, 5	0.47	Reject
663	5.67	Context Mover's Distance & Barycenters: Optimal Transport Of Contexts For Building Representations	4, 6, 7	1.25	Reject
664	5.67	Human-level Protein Localization With Convolutional Neural Networks	4, 5, 8	1.70	Accept (Poster)
665	5.67	Better Generalization With On-the-fly Dataset Denoising	5, 6, 6	0.47	Reject
666	5.67	Adaptive Pruning Of Neural Language Models For Mobile Devices	6, 5, 6	0.47	Reject
667	5.67	On Difficulties Of Probability Distillation	5, 7, 5	0.94	Reject
668	5.67	Improved Learning Of One-hidden-layer Convolutional Neural Networks With Overlaps	6, 5, 6	0.47	Reject
669	5.67	Fast Adversarial Training For Semi-supervised Learning	7, 5, 5	0.94	Reject
670	5.67	Amortized Context Vector Inference For Sequence-to-sequence Networks	6, 6, 5	0.47	Reject
671	5.67	Predicted Variables In Programming	5, 5, 7	0.94	Reject
672	5.67	Guiding Physical Intuition With Neural Stethoscopes	6, 4, 7	1.25	Reject
673	5.67	Optimal Transport Maps For Distribution Preserving Operations On Latent Spaces Of Generative Models	7, 5, 5	0.94	Accept (Poster)
674	5.67	Towards Understanding Regularization In Batch Normalization	5, 6, 6	0.47	Accept (Poster)
675	5.67	Hierarchically-structured Variational Autoencoders For Long Text Generation	5, 5, 7	0.94	Reject
676	5.67	Learning To Augment Influential Data	6, 6, 5	0.47	Reject
677	5.67	Actor-attention-critic For Multi-agent Reinforcement Learning	6, 7, 4	1.25	Reject
678	5.67	A Unified Theory Of Adaptive Stochastic Gradient Descent As Bayesian Filtering	5, 7, 5	0.94	Reject
679	5.67	Deep Probabilistic Video Compression	6, 5, 6	0.47	Reject
680	5.67	Rethinking Knowledge Graph Propagation For Zero-shot Learning	7, 5, 5	0.94	N/A
681	5.67	The Unusual Effectiveness Of Averaging In Gan Training	5, 6, 6	0.47	Accept (Poster)
682	5.67	Zero-resource Multilingual Model Transfer: Learning What To Share	6, 5, 6	0.47	Reject
683	5.67	The Meaning Of "most" For Visual Question Answering Models	7, 5, 5	0.94	Reject
684	5.67	Spectral Inference Networks: Unifying Deep And Spectral Learning	5, 7, 5	0.94	Accept (Poster)
685	5.67	Neural Persistence: A Complexity Measure For Deep Neural Networks Using Algebraic Topology	6, 4, 7	1.25	Accept (Poster)
686	5.50	Unlabeled Disentangling Of Gans With Guided Siamese Networks	5, 6, 5, 6	0.50	Reject
687	5.50	Are Generative Classifiers More Robust To Adversarial Attacks?	4, 6, 4, 8	1.66	Reject
688	5.50	Convergent Reinforcement Learning With Function Approximation: A Bilevel Optimization Perspective	5, 6, 6, 5	0.50	Reject
689	5.50	Multi-way Encoding For Robustness To Adversarial Attacks	4, 6, 6, 6	0.87	Reject
690	5.50	Music Transformer: Generating Music With Long-term Structure	7, 6, 4, 5	1.12	Accept (Poster)
691	5.50	Caml: Fast Context Adaptation Via Meta-learning	4, 6, 6, 6	0.87	Reject
692	5.50	Sample Efficient Imitation Learning For Continuous Control	5, 7, 5, 5	0.87	Accept (Poster)
693	5.33	Diffranet: Automatic Classification Of Serial Crystallography Diffraction Patterns	5, 3, 8	2.05	Reject
694	5.33	Learning To Decompose Compound Questions With Reinforcement Learning	6, 5, 5	0.47	Reject
695	5.33	Probabilistic Model-based Dynamic Architecture Search	5, 6, 5	0.47	Reject
696	5.33	Composing Entropic Policies Using Divergence Correction	4, 7, 5	1.25	Reject
697	5.33	Zero-shot Learning For Speech Recognition With Universal Phonetic Model	7, 4, 5	1.25	Reject
698	5.33	Clinical Risk: Wavelet Reconstruction Networks For Marked Point Processes	7, 4, 5	1.25	Reject
699	5.33	Graph2seq: Graph To Sequence Learning With Attention-based Neural Networks	6, 6, 4	0.94	Reject
700	5.33	Knowledge Distillation From Few Samples	4, 6, 6	0.94	Reject
701	5.33	Caveats For Information Bottleneck In Deterministic Scenarios	2, 8, 6	2.49	Accept (Poster)
702	5.33	Mimicking Actions Is A Good Strategy For Beginners: Fast Reinforcement Learning With Expert Action Sequences	5, 5, 6	0.47	Reject
703	5.33	Rethinking Learning Rate Schedules For Stochastic Optimization	6, 4, 6	0.94	Reject
704	5.33	Consistent Jumpy Predictions For Videos And Scenes	7, 4, 5	1.25	Reject
705	5.33	Adapting Auxiliary Losses Using Gradient Similarity	4, 6, 6	0.94	Reject
706	5.33	I Know The Feeling: Learning To Converse With Empathy	4, 7, 5	1.25	Reject
707	5.33	Learning From The Experience Of Others: Approximate Empirical Bayes In Neural Networks	6, 3, 7	1.70	Reject
708	5.33	Hierarchically Clustered Representation Learning	5, 5, 6	0.47	Reject
709	5.33	Learning To Refer To 3d Objects With Natural Language	6, 6, 4	0.94	Reject
710	5.33	Advocacy Learning	4, 4, 8	1.89	Reject
711	5.33	Area Attention	6, 5, 5	0.47	Reject
712	5.33	An Active Learning Framework For Efficient Robust Policy Search	5, 6, 5	0.47	Reject
713	5.33	Selective Convolutional Units: Improving Cnns Via Channel Selectivity	6, 5, 5	0.47	Reject
714	5.33	Improved Robustness To Adversarial Examples Using Lipschitz Regularization Of The Loss	6, 6, 4	0.94	Reject
715	5.33	Classification From Positive, Unlabeled And Biased Negative Data	5, 6, 5	0.47	Reject
716	5.33	Sliced Wasserstein Auto-encoders	6, 4, 6	0.94	Accept (Poster)
717	5.33	Learning To Encode Spatial Relations From Natural Language	6, 5, 5	0.47	Reject
718	5.33	Learning To Separate Domains In Generalized Zero-shot And Open Set Learning: A Probabilistic Perspective	5, 5, 6	0.47	Reject
719	5.33	Sorting Out Lipschitz Function Approximation	7, 5, 4	1.25	Reject
720	5.33	Meta-learning For Contextual Bandit Exploration	7, 6, 3	1.70	Reject
721	5.33	Systematic Generalization: What Is Required And Can It Be Learned?	4, 6, 6	0.94	Accept (Poster)
722	5.33	Local Image-to-image Translation Via Pixel-wise Highway Adaptive Instance Normalization	6, 5, 5	0.47	Reject
723	5.33	Negotiating Team Formation Using Deep Reinforcement Learning	5, 6, 5	0.47	Reject
724	5.33	Making Convolutional Networks Shift-invariant Again	6, 5, 5	0.47	Reject
725	5.33	Characterizing Attacks On Deep Reinforcement Learning	5, 5, 6	0.47	Reject
726	5.33	The Nonlinearity Coefficient - Predicting Generalization In Deep Neural Networks	5, 7, 4	1.25	Reject
727	5.33	Learning Global Additive Explanations For Neural Nets Using Model Distillation	6, 4, 6	0.94	Reject
728	5.33	Open Loop Hyperparameter Optimization And Determinantal Point Processes	5, 6, 5	0.47	Reject
729	5.33	Complementary-label Learning For Arbitrary Losses And Models	5, 5, 6	0.47	Reject
730	5.33	Mitigating Bias In Natural Language Inference Using Adversarial Learning	4, 4, 8	1.89	N/A
731	5.33	A Deep Learning Approach For Dynamic Survival Analysis With Competing Risks	4, 8, 4	1.89	Reject
732	5.33	Cdeepex: Contrastive Deep Explanations	5, 6, 5	0.47	Reject
733	5.33	Surprising Negative Results For Generative Adversarial Tree Search	5, 5, 6	0.47	Reject
734	5.33	Tangent-normal Adversarial Regularization For Semi-supervised Learning	5, 4, 7	1.25	N/A
735	5.33	The Expressive Power Of Gated Recurrent Units As A Continuous Dynamical System	5, 6, 5	0.47	Reject
736	5.33	Learning To Coordinate Multiple Reinforcement Learning Agents For Diverse Query Reformulation	4, 7, 5	1.25	Reject
737	5.33	Domain Adaptation Via Distribution And Representation Matching: A Case Study On Training Data Selection Via Reinforcement Learning	4, 7, 5	1.25	Reject
738	5.33	Optimal Margin Distribution Network	5, 6, 5	0.47	Reject
739	5.33	Generalization And Regularization In Dqn	6, 5, 5	0.47	Reject
740	5.33	Unsupervised Conditional Generation Using Noise Engineered Mode Matching Gan	5, 5, 6	0.47	Reject
741	5.33	Improved Language Modeling By Decoding The Past	6, 7, 3	1.70	Reject
742	5.33	Adversarial Sampling For Active Learning	6, 5, 5	0.47	Reject
743	5.33	Multi-task Learning With Gradient Communication	5, 4, 7	1.25	Reject
744	5.33	Quality Evaluation Of Gans Using Cross Local Intrinsic Dimensionality	4, 6, 6	0.94	Reject
745	5.33	Perfect Match: A Simple Method For Learning Representations For Counterfactual Inference With Neural Networks	5, 5, 6	0.47	Reject
746	5.33	Dynamic Planning Networks	4, 6, 6	0.94	Reject
747	5.33	Provable Guarantees On Learning Hierarchical Generative Models With Deep Cnns	6, 6, 4	0.94	Reject
748	5.33	Dataset Distillation	5, 6, 5	0.47	Reject
749	5.33	Simple Black-box Adversarial Attacks	6, 6, 4	0.94	Reject
750	5.33	Probabilistic Knowledge Graph Embeddings	5, 6, 5	0.47	Reject
751	5.33	Graph Neural Networks With Generated Parameters For Relation Extraction	4, 6, 6	0.94	Reject
752	5.33	On Learning Heteroscedastic Noise Models Within Differentiable Bayes Filters	6, 4, 6	0.94	Reject
753	5.33	Live Face De-identification In Video	6, 4, 6	0.94	N/A
754	5.33	Meta Learning With Fast/slow Learners	5, 6, 5	0.47	Reject
755	5.33	Curiosity-driven Experience Prioritization Via Density Estimation	6, 4, 6	0.94	Reject
756	5.33	Integrated Steganography And Steganalysis With Generative Adversarial Networks	5, 6, 5	0.47	Reject
757	5.33	Entropic Gans Meet Vaes: A Statistical Approach To Compute Sample Likelihoods In Gans	5, 5, 6	0.47	Reject
758	5.33	Probabilistic Federated Neural Matching	4, 6, 6	0.94	Reject
759	5.33	Local Binary Pattern Networks For Character Recognition	5, 6, 5	0.47	Reject
760	5.33	Out-of-sample Extrapolation With Neuron Editing	5, 5, 6	0.47	Reject
761	5.33	Large-scale Visual Speech Recognition	4, 3, 9	2.62	Reject
762	5.33	Knows When It Doesn’t Know: Deep Abstaining Classifiers	6, 5, 5	0.47	Reject
763	5.33	Connecting The Dots Between Mle And Rl For Sequence Generation	5, 6, 5	0.47	Reject
764	5.33	Neural Predictive Belief Representations	4, 7, 5	1.25	Reject
765	5.33	Hint-based Training For Non-autoregressive Translation	6, 6, 4	0.94	Reject
766	5.33	Neural Model-based Reinforcement Learning For Recommendation	5, 6, 5	0.47	Reject
767	5.33	Domain Generalization Via Invariant Representation Under Domain-class Dependency	4, 7, 5	1.25	Reject
768	5.33	Model Compression With Generative Adversarial Networks	5, 6, 5	0.47	Reject
769	5.33	Learning Partially Observed Pde Dynamics With Neural Networks	6, 5, 5	0.47	Reject
770	5.33	Heated-up Softmax Embedding	8, 3, 5	2.05	Reject
771	5.33	Transformer-xl: Language Modeling With Longer-term Dependency	6, 6, 4	0.94	Reject
772	5.33	Improving Composition Of Sentence Embeddings Through The Lens Of Statistical Relational Learning	5, 5, 6	0.47	Reject
773	5.33	Invariant-equivariant Representation Learning For Multi-class Data	7, 5, 4	1.25	Reject
774	5.33	Training Generative Latent Models By Variational F-divergence Minimization	6, 5, 5	0.47	Reject
775	5.33	Decaynet: A Study On The Cell States Of Long Short Term Memories	8, 4, 4	1.89	Reject
776	5.33	Label Propagation Networks	5, 5, 6	0.47	Reject
777	5.33	Augment Your Batch: Better Training With Larger Batches	4, 8, 4	1.89	Reject
778	5.33	Deep Learning Generalizes Because The Parameter-function Map Is Biased Towards Simple Functions	7, 5, 4	1.25	Accept (Poster)
779	5.33	Towards Gan Benchmarks Which Require Generalization	6, 7, 3	1.70	Accept (Poster)
780	5.33	Mahinet: A Neural Network For Many-class Few-shot Learning With Class Hierarchy	5, 6, 5	0.47	Reject
781	5.33	Learning To Describe Scenes With Programs	6, 4, 6	0.94	Accept (Poster)
782	5.33	Meta-learning Neural Bloom Filters	3, 6, 7	1.70	Reject
783	5.33	Cohen Welling Bases & So(2)-equivariant Classifiers Using Tensor Nonlinearity.	3, 7, 6	1.70	Reject
784	5.33	Antman: Sparse Low-rank Compression To Accelerate Rnn Inference	6, 5, 5	0.47	Reject
785	5.33	Learning Internal Dense But External Sparse Structures Of Deep Neural Network	5, 5, 6	0.47	Reject
786	5.33	Generative Adversarial Networks For Extreme Learned Image Compression	6, 6, 4	0.94	Reject
787	5.33	Adaptive Neural Trees	4, 6, 6	0.94	Reject
788	5.33	Graph Classification With Geometric Scattering	5, 6, 5	0.47	Reject
789	5.33	Point Cloud Gan	5, 5, 6	0.47	Reject
790	5.33	Search-guided, Lightly-supervised Training Of Structured Prediction Energy Networks	5, 7, 4	1.25	Reject
791	5.33	Exploring Curvature Noise In Large-batch Stochastic Optimization	5, 6, 5	0.47	Reject
792	5.33	Nsga-net: A Multi-objective Genetic Algorithm For Neural Architecture Search	6, 5, 5	0.47	Reject
793	5.33	Massively Parallel Hyperparameter Tuning	6, 5, 5	0.47	Reject
794	5.33	Learning And Planning With A Semantic Model	4, 7, 5	1.25	Reject
795	5.33	Playing The Game Of Universal Adversarial Perturbations	6, 5, 5	0.47	Reject
796	5.33	Learning To Adapt In Dynamic, Real-world Environments Through Meta-reinforcement Learning	7, 2, 7	2.36	Accept (Poster)
797	5.33	Bliss In Non-isometric Embedding Spaces	4, 6, 6	0.94	Reject
798	5.33	An Experimental Study Of Layer-level Training Speed And Its Impact On Generalization	6, 5, 5	0.47	Reject
799	5.33	Coverage And Quality Driven Training Of Generative Image Models	5, 4, 7	1.25	Reject
800	5.33	Multi-agent Deep Reinforcement Learning With Extremely Noisy Observations	7, 3, 6	1.70	Reject
801	5.33	Volumetric Convolution: Automatic Representation Learning In Unit Ball	6, 5, 5	0.47	Reject
802	5.33	Stackelberg Gan: Towards Provable Minimax Equilibrium Via Multi-generator Architectures	5, 7, 4	1.25	Reject
803	5.33	Exploring And Enhancing The Transferability Of Adversarial Examples	4, 6, 6	0.94	Reject
804	5.33	On The Ineffectiveness Of Variance Reduced Optimization For Deep Learning	5, 6, 5	0.47	Reject
805	5.33	Skip-gram Word Embeddings In Hyperbolic Space	5, 5, 6	0.47	Reject
806	5.33	The Case For Full-matrix Adaptive Regularization	6, 5, 5	0.47	Reject
807	5.33	Policy Optimization Via Stochastic Recursive Gradient Algorithm	5, 6, 5	0.47	Reject
808	5.33	The Universal Approximation Power Of Finite-width Deep Relu Networks	5, 5, 6	0.47	Reject
809	5.33	Synonymnet: Multi-context Bilateral Matching For Entity Synonyms	5, 7, 4	1.25	Reject
810	5.33	Convolutional Neural Networks On Non-uniform Geometrical Signals Using Euclidean Spectral Transformation	5, 7, 4	1.25	Accept (Poster)
811	5.33	Coco-gan: Conditional Coordinate Generative Adversarial Network	6, 6, 4	0.94	Reject
812	5.33	Neural Causal Discovery With Learnable Input Noise	4, 4, 8	1.89	Reject
813	5.33	Learning Graph Decomposition	7, 4, 5	1.25	N/A
814	5.33	Exploiting Cross-lingual Subword Similarities In Low-resource Document Classification	4, 6, 6	0.94	Reject
815	5.33	Towards Decomposed Linguistic Representation With Holographic Reduced Representation	5, 5, 6	0.47	Reject
816	5.33	Gaussian-gated Lstm: Improved Convergence By Reducing State Updates	5, 5, 6	0.47	Reject
817	5.33	Lorentzian Distance Learning	6, 5, 5	0.47	Reject
818	5.33	A Modern Take On The Bias-variance Tradeoff In Neural Networks	5, 7, 4	1.25	Reject
819	5.33	State-denoised Recurrent Neural Networks	6, 5, 5	0.47	Reject
820	5.33	Generative Adversarial Self-imitation Learning	5, 6, 5	0.47	Reject
821	5.33	Network Compression Using Correlation Analysis Of Layer Responses	5, 6, 5	0.47	Reject
822	5.33	Learning Generative Models For Demixing Of Structured Signals From Their Superposition Using Gans	4, 5, 7	1.25	Reject
823	5.33	Purchase As Reward : Session-based Recommendation By Imagination Reconstruction	5, 6, 5	0.47	Reject
824	5.33	Geneval: A Benchmark Suite For Evaluating Generative Models	5, 5, 6	0.47	Reject
825	5.33	Deep Graph Translation	5, 5, 6	0.47	Reject
826	5.33	Unseen Action Recognition With Unpaired Adversarial Multimodal Learning	7, 5, 4	1.25	Reject
827	5.33	Escaping Flat Areas Via Function-preserving Structural Network Modifications	6, 4, 6	0.94	Reject
828	5.33	Reducing Overconfident Errors Outside The Known Distribution	6, 4, 6	0.94	Reject
829	5.33	Low Latency Privacy Preserving Inference	5, 6, 5	0.47	Reject
830	5.33	Causal Importance Of Orientation Selectivity For Generalization In Image Recognition	7, 5, 4	1.25	Reject
831	5.33	What Would Pi* Do?: Imitation Learning Via Off-policy Reinforcement Learning	5, 5, 6	0.47	Reject
832	5.33	Engan: Latent Space Mcmc And Maximum Entropy Generators For Energy-based Models	6, 5, 5	0.47	Reject
833	5.33	Graph Transformation Policy Network For Chemical Reaction Prediction	5, 6, 5	0.47	Reject
834	5.33	Importance Resampling For Off-policy Policy Evaluation	6, 5, 5	0.47	Reject
835	5.33	Cnnsat: Fast, Accurate Boolean Satisfiability Using Convolutional Neural Networks	5, 6, 5	0.47	Reject
836	5.33	An Efficient And Margin-approaching Zero-confidence Adversarial Attack	5, 5, 6	0.47	Reject
837	5.25	Diverse Machine Translation With A Single Multinomial Latent Variable	3, 6, 5, 7	1.48	Reject
838	5.25	Optimal Attacks Against Multiple Classifiers	5, 4, 6, 6	0.83	Reject
839	5.25	Unified Recurrent Network For Many Feature Types	4, 6, 4, 7	1.30	Reject
840	5.25	An Alarm System For Segmentation Algorithm Based On Shape Model	7, 3, 6, 5	1.48	Reject
841	5.25	P^2ir: Universal Deep Node Representation Via Partial Permutation Invariant Set Functions	4, 7, 5, 5	1.09	Reject
842	5.25	Improving Generative Adversarial Imitation Learning With Non-expert Demonstrations	5, 5, 7, 4	1.09	Reject
843	5.25	Towards A Better Understanding Of Vector Quantized Autoencoders	5, 7, 3, 6	1.48	Reject
844	5.25	On The Spectral Bias Of Neural Networks	4, 6, 5, 6	0.83	Reject
845	5.20	Deep Neuroevolution: Genetic Algorithms Are A Competitive Alternative For Training Deep Neural Networks For Reinforcement Learning	6, 6, 4, 3, 7	1.47	Reject
846	5.00	Accelerated Value Iteration Via Anderson Mixing	7, 4, 4	1.41	Reject
847	5.00	A Case For Object Compositionality In Deep Generative Models Of Images	5, 4, 6	0.82	Reject
848	5.00	Guided Exploration In Deep Reinforcement Learning	7, 5, 3	1.63	Reject
849	5.00	Plan Online, Learn Offline: Efficient Learning And Exploration Via Model-based Control	6, 5, 4	0.82	Accept (Poster)
850	5.00	K-nearest Neighbors By Means Of Sequence To Sequence Deep Neural Networks And Memory Networks	6, 5, 4	0.82	Reject
851	5.00	Mlprune: Multi-layer Pruning For Automated Neural Network Compression	5, 6, 4	0.82	Reject
852	5.00	The Anisotropic Noise In Stochastic Gradient Descent: Its Behavior Of Escaping From Minima And Regularization Effects	4, 6, 5	0.82	Reject
853	5.00	Transfer Learning For Estimating Causal Effects Using Neural Networks	7, 5, 3	1.63	N/A
854	5.00	Cross-entropy Loss Leads To Poor Margins	3, 4, 8, 5, 5	1.67	Reject
855	5.00	Tequilagan: How To Easily Identify Gan Samples	4, 6, 5	0.82	Reject
856	5.00	Structured Content Preservation For Unsupervised Text Style Transfer	5, 6, 4	0.82	N/A
857	5.00	Correction Networks: Meta-learning For Zero-shot Learning	4, 4, 7	1.41	Reject
858	5.00	Nattack: A Strong And Universal Gaussian Black-box Adversarial Attack	7, 4, 4	1.41	Reject
859	5.00	Where And When To Look? Spatial-temporal Attention For Action Recognition In Videos	6, 3, 6	1.41	Reject
860	5.00	Adversarial Audio Super-resolution With Unsupervised Feature Losses	4, 5, 6	0.82	Reject
861	5.00	An Adversarial Learning Framework For A Persona-based Multi-turn Dialogue Model	6, 4, 5	0.82	Reject
862	5.00	Zero-shot Dual Machine Translation	4, 6, 5	0.82	Reject
863	5.00	Learning To Progressively Plan	5, 5, 5	0.00	Reject
864	5.00	Deep Clustering Based On A Mixture Of Autoencoders	6, 4, 5	0.82	N/A
865	5.00	What Is In A Translation Unit? Comparing Character And Subword Representations Beyond Translation	5, 5, 5	0.00	N/A
866	5.00	Learning To Remember: Dynamic Generative Memory For Continual Learning	4, 3, 8	2.16	Reject
867	5.00	A Recurrent Neural Cascade-based Model For Continuous-time Diffusion Process	7, 4, 4	1.41	Reject
868	5.00	Nesterov's Method Is The Discretization Of A Differential Equation With Hessian Damping	4, 5, 6	0.82	N/A
869	5.00	Representation-constrained Autoencoders And An Application To Wireless Positioning	5, 4, 6	0.82	Reject
870	5.00	Towards Resisting Large Data Variations Via Introspective Learning	4, 5, 6	0.82	N/A
871	5.00	Transferrable End-to-end Learning For Protein Interface Prediction	5, 5, 5	0.00	Reject
872	5.00	Learning Joint Wasserstein Auto-encoders For Joint Distribution Matching	6, 5, 4	0.82	Reject
873	5.00	Incremental Few-shot Learning With Attention Attractor Networks	5, 5, 5	0.00	Reject
874	5.00	Learning With Random Learning Rates.	6, 4, 5	0.82	Reject
875	5.00	Bias Also Matters: Bias Attribution For Deep Neural Network Explanation	5, 5, 5	0.00	Reject
876	5.00	Engaging Image Captioning Via Personality	5, 5, 5	0.00	N/A
877	5.00	Generative Adversarial Models For Learning Private And Fair Representations	4, 4, 7	1.41	Reject
878	5.00	The Gan Landscape: Losses, Architectures, Regularization, And Normalization	4, 4, 7	1.41	Reject
879	5.00	Generative Ensembles For Robust Anomaly Detection	5, 4, 6	0.82	Reject
880	5.00	Backplay: 'man Muss Immer Umkehren'	5, 5, 5	0.00	Reject
881	5.00	Learning Diverse Generations Using Determinantal Point Processes	5, 5, 5	0.00	Reject
882	5.00	Conditional Network Embeddings	4, 6, 5	0.82	Accept (Poster)
883	5.00	Co-manifold Learning With Missing Data	4, 4, 7	1.41	Reject
884	5.00	Dynamic Graph Representation Learning Via Self-attention Networks	4, 6, 5	0.82	Reject
885	5.00	Noisy Information Bottlenecks For Generalization	7, 5, 3	1.63	Reject
886	5.00	Directional Analysis Of Stochastic Gradient Descent Via Von Mises-fisher Distributions In Deep Learning	6, 5, 4	0.82	Reject
887	5.00	Choicenet: Robust Learning By Revealing Output Correlations	4, 6, 5	0.82	Reject
888	5.00	Neural Message Passing For Multi-label Classification	4, 6, 5	0.82	Reject
889	5.00	Riemannian Transe: Multi-relational Graph Embedding In Non-euclidean Space	5, 5, 5	0.00	Reject
890	5.00	Ada-boundary: Accelerating The Dnn Training Via Adaptive Boundary Batch Selection	5, 5, 5	0.00	Reject
891	5.00	Deep Curiosity Search: Intra-life Exploration Can Improve Performance On Challenging Deep Reinforcement Learning Problems	5, 5, 5	0.00	Reject
892	5.00	Intrinsic Social Motivation Via Causal Influence In Multi-agent Rl	5, 4, 6	0.82	Reject
893	5.00	Empirical Observations On The Instability Of Aligning Word Vector Spaces With Gans	4, 6, 5	0.82	N/A
894	5.00	Analyzing Federated Learning Through An Adversarial Lens	5, 4, 6	0.82	Reject
895	5.00	Variational Smoothing In Recurrent Neural Network Language Models	7, 6, 2	2.16	Accept (Poster)
896	5.00	Stop Memorizing: A Data-dependent Regularization Framework For Intrinsic Pattern Learning	7, 4, 4	1.41	Reject
897	5.00	Probabilistic Semantic Embedding	7, 4, 4	1.41	Reject
898	5.00	Globally Soft Filter Pruning For Efficient Convolutional Neural Networks	6, 5, 4	0.82	Reject
899	5.00	The Effectiveness Of Pre-trained Code Embeddings	6, 4, 5	0.82	Reject
900	5.00	Discovering Low-precision Networks Close To Full-precision Networks For Efficient Embedded Inference	5, 4, 6	0.82	Reject
901	5.00	On The Relationship Between Neural Machine Translation And Word Alignment	4, 5, 6	0.82	Reject
902	5.00	Cautious Deep Learning	4, 7, 4	1.41	Reject
903	5.00	End-to-end Learning Of A Convolutional Neural Network Via Deep Tensor Decomposition	5, 5, 5	0.00	N/A
904	5.00	Few-shot Classification On Graphs With Structural Regularized Gcns	4, 6, 5	0.82	Reject
905	5.00	A Better Baseline For Second Order Gradient Estimation In Stochastic Computation Graphs	6, 5, 6, 3	1.22	Reject
906	5.00	Unsupervised Multi-target Domain Adaptation: An Information Theoretic Approach	6, 4, 5	0.82	Reject
907	5.00	Improving Gaussian Mixture Latent Variable Model Convergence With Optimal Transport	5, 5, 5	0.00	N/A
908	5.00	Spatial-winograd Pruning Enabling Sparse Winograd Convolution	5, 4, 6	0.82	Reject
909	5.00	Towards Language Agnostic Universal Representations	5, 4, 6	0.82	Reject
910	5.00	Generative Adversarial Network Training Is A Continual Learning Problem	5, 3, 7	1.63	Reject
911	5.00	Local Stability And Performance Of Simple Gradient Penalty -wasserstein Gan	5, 4, 6	0.82	Reject
912	5.00	Understand The Dynamics Of Gans Via Primal-dual Optimization	4, 5, 6	0.82	Reject
913	5.00	A Main/subsidiary Network Framework For Simplifying Binary Neural Networks	5	0.00	N/A
914	5.00	Implicit Autoencoders	3, 6, 6	1.41	Reject
915	5.00	Excitation Dropout: Encouraging Plasticity In Deep Neural Networks	5, 5, 5	0.00	Reject
916	5.00	Convergence Properties Of Deep Neural Networks On Separable Data	5, 5, 5	0.00	Reject
917	5.00	Weakly-supervised Knowledge Graph Alignment With Adversarial Learning	5, 5, 5	0.00	Reject
918	5.00	Quantization For Rapid Deployment Of Deep Neural Networks	5, 5, 5	0.00	Reject
919	5.00	Harmonic Unpaired Image-to-image Translation	6, 5, 4	0.82	Accept (Poster)
920	5.00	On The Effectiveness Of Task Granularity For Transfer Learning	5, 5, 5	0.00	Reject
921	5.00	Relwalk -- A Latent Variable Model Approach To Knowledge Graph Embedding	6, 5, 4	0.82	Reject
922	5.00	Likelihood-based Permutation Invariant Loss Function For Probability Distributions	5, 6, 4	0.82	Reject
923	5.00	Link Prediction In Hypergraphs Using Graph Convolutional Networks	6, 5, 4	0.82	Reject
924	5.00	Physiological Signal Embeddings (phase) Via Interpretable Stacked Models	6, 5, 4	0.82	Reject
925	5.00	Transferring Slu Models In Novel Domains	6, 5, 4	0.82	Reject
926	5.00	Deep Reinforcement Learning Of Universal Policies With Diverse Environment Summaries	4, 6, 5	0.82	Reject
927	5.00	A Privacy-preserving Image Classification Framework With A Learnable Obfuscator	5, 5, 5	0.00	N/A
928	5.00	Optimistic Acceleration For Optimization	5, 6, 5, 4	0.71	Reject
929	5.00	Metric-optimized Example Weights	4, 4, 7	1.41	Reject
930	5.00	Novel Positional Encodings To Enable Tree-structured Transformers	5, 4, 6	0.82	Reject
931	5.00	The Importance Of Norm Regularization In Linear Graph Embedding: Theoretical Analysis And Empirical Demonstration	7, 4, 4	1.41	Reject
932	5.00	Analysis Of Memory Organization For Dynamic Neural Networks	7, 5, 3	1.63	Reject
933	5.00	Isa-vae: Independent Subspace Analysis With Variational Autoencoders	4, 7, 4	1.41	Reject
934	5.00	Inferring Reward Functions From Demonstrators With Unknown Biases	5, 5, 5	0.00	Reject
935	5.00	Approximation Capability Of Neural Networks On Sets Of Probability Measures And Tree-structured Data	6, 5, 4	0.82	Reject
936	5.00	Denoise While Aggregating: Collaborative Learning In Open-domain Question Answering	4, 6, 5	0.82	Reject
937	5.00	Learning Discriminators As Energy Networks In Adversarial Learning	5, 5, 5	0.00	Reject
938	5.00	Learning Representations Of Categorical Feature Combinations Via Self-attention	5, 5, 5	0.00	Reject
939	5.00	Therml: The Thermodynamics Of Machine Learning	7, 3, 5	1.63	Reject
940	5.00	Favae: Sequence Disentanglement Using In- Formation Bottleneck Principle	5, 6, 4	0.82	Reject
941	5.00	Learning Representations Of Sets Through Optimized Permutations	6, 3, 6	1.41	Accept (Poster)
942	5.00	Convolutional Neural Networks Combined With Runge-kutta Methods	4, 5, 6	0.82	Reject
943	5.00	Supportnet: Solving Catastrophic Forgetting In Class Incremental Learning With Support Data	6, 5, 4	0.82	Reject
944	5.00	Experience Replay For Continual Learning	5, 5, 5	0.00	Reject
945	5.00	Hypergan: Exploring The Manifold Of Neural Networks	6, 5, 4	0.82	Reject
946	5.00	Learning Neuron Non-linearities With Kernel-based Deep Neural Networks	5, 4, 6	0.82	Reject
947	5.00	Pairwise Augmented Gans With Adversarial Reconstruction Loss	4, 6, 5	0.82	Reject
948	5.00	Cutting Down Training Memory By Re-fowarding	6, 4, 4, 6	1.00	Reject
949	5.00	Multi-modal Generative Adversarial Networks For Diverse Datasets	4, 6	1.00	N/A
950	5.00	A Variational Autoencoder For Probabilistic Non-negative Matrix Factorisation	4, 4, 7	1.41	Reject
951	5.00	High Resolution And Fast Face Completion Via Progressively Attentive Gans	5, 5, 5	0.00	Reject
952	5.00	Redsync : Reducing Synchronization Traffic For Distributed Deep Learning	5, 5, 5	0.00	Reject
953	5.00	What A Difference A Pixel Makes: An Empirical Examination Of Features Used By Cnns For Categorisation	4, 4, 7	1.41	Reject
954	5.00	Graph2seq: Scalable Learning Dynamics For Graphs	6, 5, 4	0.82	Reject
955	5.00	Self-binarizing Networks	5, 5, 5	0.00	N/A
956	5.00	Dissecting An Adversarial Framework For Information Retrieval	6, 5, 4	0.82	Reject
957	5.00	Capacity Of Deep Neural Networks Under Parameter Quantization	5, 5, 5	0.00	N/A
958	5.00	Model Comparison For Semantic Grouping	5, 5, 5	0.00	Reject
959	5.00	Learning Abstract Models For Long-horizon Exploration	4, 5, 6	0.82	Reject
960	5.00	Finding Mixed Nash Equilibria Of Generative Adversarial Networks	4, 5, 6	0.82	Reject
961	5.00	Pointgrow: Autoregressively Learned Point Cloud Generation With Self-attention	3, 6, 6	1.41	N/A
962	5.00	Information Maximization Auto-encoding	5, 6, 4	0.82	Reject
963	5.00	Bayesian Deep Learning Via Stochastic Gradient Mcmc With A Stochastic Approximation Adaptation	5, 4, 6	0.82	Reject
964	5.00	Boosting Robustness Certification Of Neural Networks	5, 6, 4	0.82	Accept (Poster)
965	5.00	Vhegan: Variational Hetero-encoder Randomized Gan For Zero-shot Learning	5, 5, 5	0.00	Reject
966	5.00	Inducing Cooperation Via Learning To Reshape Rewards In Semi-cooperative Multi-agent Reinforcement Learning	5, 5, 5	0.00	Reject
967	5.00	Iteratively Learning From The Best	6, 3, 6	1.41	Reject
968	5.00	Déjà Vu: An Empirical Evaluation Of The Memorization Properties Of Convnets	4, 5, 6	0.82	Reject
969	5.00	Understanding The Effectiveness Of Lipschitz-continuity In Generative Adversarial Nets	6, 4, 5	0.82	Reject
970	5.00	Efficient Codebook And Factorization For Second Order Representation Learning	4, 6, 5	0.82	Reject
971	5.00	Reinforced Imitation Learning From Observations	6, 5, 4	0.82	Reject
972	5.00	Safe Policy Learning From Observations	5, 5, 5	0.00	Reject
973	5.00	Data Interpretation And Reasoning Over Scientific Plots	6, 6, 3	1.41	N/A
974	5.00	An Energy-based Framework For Arbitrary Label Noise Correction	5, 5, 5	0.00	Reject
975	5.00	Discrete Flow Posteriors For Variational Inference In Discrete Dynamical Systems	4, 4, 7	1.41	Reject
976	5.00	Human-guided Column Networks: Augmenting Deep Learning With Advice	6, 4, 5	0.82	Reject
977	5.00	Collaborative Multiagent Reinforcement Learning In Homogeneous Swarms	6, 4, 5	0.82	Reject
978	5.00	An Automatic Operation Batching Strategy For The Backward Propagation Of Neural Networks Having Dynamic Computation Graphs	5, 6, 4	0.82	Reject
979	5.00	Unicorn: Continual Learning With A Universal, Off-policy Agent	4, 5, 6	0.82	Reject
980	5.00	A Theoretical Framework For Deep And Locally Connected Relu Network	3, 7, 5	1.63	Reject
981	5.00	On Regularization And Robustness Of Deep Neural Networks	5, 4, 6	0.82	Reject
982	5.00	Strength In Numbers: Trading-off Robustness And Computation Via Adversarially-trained Ensembles	5, 6, 4	0.82	Reject
983	5.00	Canonical Correlation Analysis With Implicit Distributions	5, 6, 4	0.82	Reject
984	5.00	Dense Morphological Network: An Universal Function Approximator	5, 5, 5	0.00	Reject
985	5.00	Ad-vat: An Asymmetric Dueling Mechanism For Learning Visual Active Tracking	5, 4, 6	0.82	Accept (Poster)
986	5.00	Double Neural Counterfactual Regret Minimization	5, 6, 4	0.82	Reject
987	5.00	Guided Evolutionary Strategies: Escaping The Curse Of Dimensionality In Random Search	5, 4, 6	0.82	Reject
988	5.00	Using Ontologies To Improve Performance In Massively Multi-label Prediction	6, 5, 4	0.82	Reject
989	5.00	Accelerated Gradient Flow For Probability Distributions	4, 5, 6	0.82	Reject
990	5.00	Large Batch Size Training Of Neural Networks With Adversarial Training And Second-order Information	4, 7, 4	1.41	Reject
991	5.00	Phrase-based Attentions	5, 5, 5	0.00	Reject
992	5.00	Causal Reasoning From Meta-reinforcement Learning	5, 4, 4, 7	1.22	Reject
993	5.00	Interpretable Continual Learning	4, 5, 6	0.82	Reject
994	5.00	Tensor Ring Nets Adapted Deep Multi-task Learning	6, 5, 4	0.82	Reject
995	5.00	Reduced-gate Convolutional Lstm Design Using Predictive Coding For Next-frame Video Prediction	5, 3, 7	1.63	Reject
996	5.00	S3ta: A Soft, Spatial, Sequential, Top-down Attention Model	5, 5, 5	0.00	Reject
997	5.00	Solar: Deep Structured Representations For Model-based Reinforcement Learning	5, 5, 5	0.00	Reject
998	5.00	Learning To Control Self-assembling Morphologies: A Study Of Generalization Via Modularity	4, 7, 4	1.41	Reject
999	5.00	Snapquant: A Probabilistic And Nested Parameterization For Binary Networks	4, 6, 5	0.82	Reject
1000	5.00	Spread Divergences	5, 4, 6	0.82	Reject
1001	5.00	Characterizing Malicious Edges Targeting On Graph Neural Networks	5, 5, 5	0.00	Reject
1002	5.00	N-ary Quantization For Cnn Model Compression And Inference Acceleration	4, 4, 7	1.41	Reject
1003	4.75	Pooling Is Neither Necessary Nor Sufficient For Appropriate Deformation Stability In Cnns	5, 4, 5, 5	0.43	Reject
1004	4.75	Geomstats: A Python Package For Riemannian Geometry In Machine Learning	4, 4, 3, 8	1.92	Reject
1005	4.75	Multi-turn Dialogue Response Generation In An Adversarial Learning Framework	4, 4, 6, 5	0.83	Reject
1006	4.75	Successor Options : An Option Discovery Algorithm For Reinforcement Learning	4, 5, 6, 4	0.83	Reject
1007	4.67	Like What You Like: Knowledge Distill Via Neuron Selectivity Transfer	4, 4, 6	0.94	Reject
1008	4.67	A Study Of Robustness Of Neural Nets Using Approximate Feature Collisions	6, 4, 4	0.94	Reject
1009	4.67	Segen: Sample-ensemble Genetic Evolutionary Network Model	5, 5, 4	0.47	Reject
1010	4.67	Unsupervised Disentangling Structure And Appearance	6, 5, 3	1.25	Reject
1011	4.67	Predictive Uncertainty Through Quantization	5, 4, 5	0.47	Reject
1012	4.67	Shaping Representations Through Communication	5, 4, 5	0.47	N/A
1013	4.67	Diagnosing Language Inconsistency In Cross-lingual Word Embeddings	6, 4, 4	0.94	N/A
1014	4.67	Explicit Recall For Efficient Exploration	7, 4, 3	1.70	Reject
1015	4.67	Generalized Adaptive Moment Estimation	3, 4, 7	1.70	Reject
1016	4.67	Neural Variational Inference For Embedding Knowledge Graphs	5, 5, 4	0.47	Reject
1017	4.67	Holographic And Other Point Set Distances For Machine Learning	4, 3, 7	1.70	Reject
1018	4.67	Geometry Aware Convolutional Filters For Omnidirectional Images Representation	4, 6, 4	0.94	Reject
1019	4.67	End-to-end Learning Of Pharmacological Assays From High-resolution Microscopy Images	6, 3, 5	1.25	Reject
1020	4.67	Ssoc: Learning Spontaneous And Self-organizing Communication For Multi-agent Collaboration	4, 5, 5	0.47	Reject
1021	4.67	Estimating Heterogeneous Treatment Effects Using Neural Networks With The Y-learner	5, 5, 4	0.47	N/A
1022	4.67	Na	4, 5, 5	0.47	N/A
1023	4.67	Computation-efficient Quantization Method For Deep Neural Networks	4, 5, 5	0.47	Reject
1024	4.67	Context-aware Forecasting For Multivariate Stationary Time-series	5, 5, 4	0.47	N/A
1025	4.67	Traditional And Heavy Tailed Self Regularization In Neural Network Models	4, 4, 6	0.94	Reject
1026	4.67	Efficient Dictionary Learning With Gradient Descent	5, 4, 5	0.47	Reject
1027	4.67	Answer-based Adversarial Training For Generating Clarification Questions	4, 6, 4	0.94	N/A
1028	4.67	Learning Hash Codes Via Hamming Distance Targets	4, 6, 4	0.94	Reject
1029	4.67	On The Convergence And Robustness Of Batch Normalization	6, 4, 4	0.94	Reject
1030	4.67	Zero-training Sentence Embedding Via Orthogonal Basis	5, 4, 5	0.47	Reject
1031	4.67	Feature Prioritization And Regularization Improve Standard Accuracy And Adversarial Robustness	5, 4, 5	0.47	Reject
1032	4.67	Probabilistic Binary Neural Networks	6, 5, 3	1.25	Reject
1033	4.67	Differential Equation Networks	5, 4, 5	0.47	Reject
1034	4.67	Stochastic Learning Of Additive Second-order Penalties With Applications To Fairness	5, 5, 4	0.47	Reject
1035	4.67	Rectified Gradient: Layer-wise Thresholding For Sharp And Coherent Attribution Maps	5, 5, 4	0.47	Reject
1036	4.67	When Will Gradient Methods Converge To Max-margin Classifier Under Relu Models?	5, 4, 5	0.47	Reject
1037	4.67	An Efficient Network For Predicting Time-varying Distributions	5, 4, 5	0.47	N/A
1038	4.67	Selectivity Metrics Can Overestimate The Selectivity Of Units: A Case Study On Alexnet	5, 6, 3	1.25	Reject
1039	4.67	Effective Path: Know The Unknowns Of Neural Network	4, 4, 6	0.94	Reject
1040	4.67	Exploiting Environmental Variation To Improve Policy Robustness In Reinforcement Learning	5, 3, 6	1.25	Reject
1041	4.67	Mean Replacement Pruning	5, 4, 5	0.47	Reject
1042	4.67	Inference Of Unobserved Event Streams With Neural Hawkes Particle Smoothing	5, 4, 5	0.47	Reject
1043	4.67	Theoretical And Empirical Study Of Adversarial Examples	5, 5, 4	0.47	Reject
1044	4.67	Domain Adaptive Transfer Learning	3, 4, 7	1.70	N/A
1045	4.67	How Training Data Affect The Accuracy And Robustness Of Neural Networks For Image Classification	4, 5, 5	0.47	Reject
1046	4.67	Learning Physics Priors For Deep Reinforcement Learing	5, 4, 5	0.47	Reject
1047	4.67	Coupled Recurrent Models For Polyphonic Music Composition	7, 3, 4	1.70	Reject
1048	4.67	Unifying Bilateral Filtering And Adversarial Training For Robust Neural Networks	4, 5, 5	0.47	Reject
1049	4.67	Effective And Efficient Batch Normalization Using Few Uncorrelated Data For Statistics' Estimation	4, 5, 5	0.47	Reject
1050	4.67	Visualizing And Discovering Behavioural Weaknesses In Deep Reinforcement Learning	5, 5, 4	0.47	N/A
1051	4.67	Improving Latent Variable Descriptiveness By Modelling Rather Than Ad-hoc Factors	4, 4, 6	0.94	N/A
1052	4.67	Accelerated Sparse Recovery Under Structured Measurements	4, 5, 5	0.47	Reject
1053	4.67	Unsupervised Expectation Learning For Multisensory Binding	4, 5, 5	0.47	Reject
1054	4.67	Crystalgan: Learning To Discover Crystallographic Structures With Generative Adversarial Networks	3, 7, 4	1.70	N/A
1055	4.67	Deep-trim: Revisiting L1 Regularization For Connection Pruning Of Deep Network	4, 6, 4	0.94	Reject
1056	4.67	Interpreting Adversarial Robustness: A View From Decision Surface In Input Space	3, 6, 5	1.25	Reject
1057	4.67	What Information Does A Resnet Compress?	4, 4, 6	0.94	Reject
1058	4.67	Highly Efficient 8-bit Low Precision Inference Of Convolutional Neural Networks	6, 4, 4	0.94	Reject
1059	4.67	Measuring Density And Similarity Of Task Relevant Information In Neural Representations	4, 5, 5	0.47	Reject
1060	4.67	Over-parameterization Improves Generalization In The Xor Detection Problem	4, 5, 5	0.47	Reject
1061	4.67	Few-shot Learning By Exploiting Object Relation	6, 4, 4	0.94	N/A
1062	4.67	N/a	4, 4, 6	0.94	N/A
1063	4.67	Improved Resistance Of Neural Networks To Adversarial Images Through Generative Pre-training	4, 4, 6	0.94	Reject
1064	4.67	Sparse Binary Compression: Towards Distributed Deep Learning With Minimal Communication	6, 3, 5	1.25	Reject
1065	4.67	Dual Skew Divergence Loss For Neural Machine Translation	3, 6, 5	1.25	Reject
1066	4.67	Discriminative Out-of-distribution Detection For Semantic Segmentation	4, 7, 3	1.70	Reject
1067	4.67	Maximum A Posteriori On A Submanifold: A General Image Restoration Method With Gan	4, 4, 6	0.94	Reject
1068	4.67	Robust Determinantal Generative Classifier For Noisy Labels And Adversarial Attacks	3, 7, 4	1.70	Reject
1069	4.67	Learned Optimizers That Outperform On Wall-clock And Validation Loss	4, 5, 5	0.47	Reject
1070	4.67	Pushing The Bounds Of Dropout	5, 5, 4	0.47	Reject
1071	4.67	Manifold Alignment Via Feature Correspondence	5, 5, 4	0.47	Reject
1072	4.67	Low-rank Matrix Factorization Of Lstm As Effective Model Compression	5, 5, 4	0.47	N/A
1073	4.67	Security Analysis Of Deep Neural Networks Operating In The Presence Of Cache Side-channel Attacks	4, 6, 4	0.94	Reject
1074	4.67	Cgnf: Conditional Graph Neural Fields	5, 4, 5	0.47	Reject
1075	4.67	Self-supervised Generalisation With Meta Auxiliary Learning	4, 4, 6	0.94	Reject
1076	4.67	An Investigation Of Model-free Planning	5, 5, 4	0.47	Reject
1077	4.67	Evolving Intrinsic Motivations For Altruistic Behavior	5, 6, 3	1.25	N/A
1078	4.67	Boosting Trust Region Policy Optimization By Normalizing Flows Policy	6, 4, 4	0.94	Reject
1079	4.67	Mixfeat: Mix Feature In Latent Space Learns Discriminative Space	6, 4, 4	0.94	Reject
1080	4.67	Unsupervised Image To Sequence Translation With Canvas-drawer Networks	4, 6, 4	0.94	Reject
1081	4.67	Chemical Names Standardization Using Neural Sequence To Sequence Model	4, 3, 7	1.70	Reject
1082	4.67	Tabnn: A Universal Neural Network Solution For Tabular Data	5, 4, 5	0.47	Reject
1083	4.67	Compound Density Networks	4, 5, 5	0.47	Reject
1084	4.67	Architecture Compression	6, 4, 4	0.94	Reject
1085	4.67	Text Infilling	3, 5, 6	1.25	Reject
1086	4.67	Approximation And Non-parametric Estimation Of Resnet-type Convolutional Neural Networks Via Block-sparse Fully-connected Neural Networks	4, 6, 4	0.94	Reject
1087	4.67	Learning Gibbs-regularized Gans With Variational Discriminator Reparameterization	5, 5, 4	0.47	Reject
1088	4.67	Learning To Attend On Essential Terms: An Enhanced Retriever-reader Model For Open-domain Question Answering	4, 5, 5	0.47	N/A
1089	4.67	Progressive Weight Pruning Of Deep Neural Networks Using Admm	5, 5, 4	0.47	Reject
1090	4.67	Tfgan: Improving Conditioning For Text-to-video Synthesis	6, 3, 5	1.25	N/A
1091	4.67	Penetrating The Fog: The Path To Efficient Cnn Models	5, 4, 5	0.47	Reject
1092	4.67	Pruning In Training: Learning And Ranking Sparse Connections In Deep Convolutional Networks	5, 5, 4	0.47	Reject
1093	4.67	Expanding The Reach Of Federated Learning By Reducing Client Resource Requirements	4, 5, 5	0.47	Reject
1094	4.67	Learning To Drive By Observing The Best And Synthesizing The Worst	3, 6, 5	1.25	Reject
1095	4.67	Multi-grained Entity Proposal Network For Named Entity Recognition	5, 5, 4	0.47	Reject
1096	4.67	Learning With Little Data: Evaluation Of Deep Learning Algorithms	6, 4, 4	0.94	N/A
1097	4.67	A Fast Quasi-newton-type Method For Large-scale Stochastic Optimisation	5, 5, 4	0.47	Reject
1098	4.67	Gradient Descent Happens In A Tiny Subspace	4, 4, 6	0.94	Reject
1099	4.67	Pumpout: A Meta Approach For Robustly Training Deep Neural Networks With Noisy Labels	6, 5, 3	1.25	Reject
1100	4.67	Convergence Guarantees For Rmsprop And Adam In Non-convex Optimization And An Empirical Comparison To Nesterov Acceleration	5, 4, 5	0.47	Reject
1101	4.67	Logically-constrained Neural Fitted Q-iteration	5, 4, 5	0.47	N/A
1102	4.67	Pa-gan: Improving Gan Training By Progressive Augmentation	4, 5, 5	0.47	Reject
1103	4.67	Learning Graph Representations By Dendrograms	4, 5, 5	0.47	Reject
1104	4.67	Outlier Detection From Image Data	4, 5, 5	0.47	Reject
1105	4.67	Count-based Exploration With The Successor Representation	5, 5, 4	0.47	Reject
1106	4.67	On Breiman’s Dilemma In Neural Networks: Success And Failure Of Normalized Margins	4, 5, 5	0.47	Reject
1107	4.67	On Accurate Evaluation Of Gans For Language Generation	5, 3, 6	1.25	Reject
1108	4.67	Noise-tempered Generative Adversarial Networks	4, 5, 5	0.47	N/A
1109	4.67	A Unified View Of Deep Metric Learning Via Gradient Analysis	3, 6, 5	1.25	N/A
1110	4.67	Ergodic Measure Preserving Flows	5, 5, 4	0.47	Reject
1111	4.67	Stability Of Stochastic Gradient Method With Momentum For Strongly Convex Loss Functions	4, 6, 4	0.94	Reject
1112	4.67	Siamese Capsule Networks	5, 6, 3	1.25	Reject
1113	4.67	Learning Shared Manifold Representation Of Images And Attributes For Generalized Zero-shot Learning	4, 5, 5	0.47	Reject
1114	4.67	Variational Sparse Coding	4, 5, 5	0.47	Reject
1115	4.67	Parameter Efficient Training Of Deep Convolutional Neural Networks By Dynamic Sparse Reparameterization	4, 4, 6	0.94	Reject
1116	4.67	Open Vocabulary Learning On Source Code With A Graph-structured Cache	4, 4, 6	0.94	Reject
1117	4.67	Simile: Introducing Sequential Information Towards More Effective Imitation Learning	6, 4, 4	0.94	Reject
1118	4.67	Differentiable Expected Bleu For Text Generation	4, 4, 6	0.94	Reject
1119	4.67	Generating Realistic Stock Market Order Streams	5, 5, 4	0.47	Reject
1120	4.67	Tinkering With Black Boxes: Counterfactuals Uncover Modularity In Generative Models	6, 4, 4	0.94	Reject
1121	4.67	Neural Malware Control With Deep Reinforcement Learning	5, 4, 5	0.47	Reject
1122	4.67	Three Continual Learning Scenarios And A Case For Generative Replay	4, 4, 6	0.94	Reject
1123	4.67	On The Geometry Of Adversarial Examples	5, 3, 6	1.25	Reject
1124	4.67	Investigating Cnns' Learning Representation Under Label Noise	5, 4, 5	0.47	Reject
1125	4.67	Integral Pruning On Activations And Weights For Efficient Neural Networks	4, 5, 5	0.47	Reject
1126	4.67	A Proposed Hierarchy Of Deep Learning Tasks	6, 4, 4	0.94	Reject
1127	4.67	3d-relnet: Joint Object And Relational Network For 3d Prediction	6, 3, 5	1.25	Reject
1128	4.67	Ace: Artificial Checkerboard Enhancer To Induce And Evade Adversarial Attacks	4, 4, 6	0.94	Reject
1129	4.67	Conscious Inference For Object Detection	4, 6, 4	0.94	Reject
1130	4.67	Sufficient Conditions For Robustness To Adversarial Examples: A Theoretical And Empirical Study With Bayesian Neural Networks	5, 5, 4	0.47	Reject
1131	4.67	Using Gans For Generation Of Realistic City-scale Ride Sharing/hailing Data Sets	4, 5, 5	0.47	Reject
1132	4.67	Visual Imitation With A Minimal Adversary	5, 3, 6	1.25	Reject
1133	4.67	Intriguing Properties Of Learned Representations	3, 6, 5	1.25	Reject
1134	4.67	Sampling With Probability Matching	5, 6, 3	1.25	Reject
1135	4.67	Meta-learning With Differentiable Closed-form Solvers	5, 2, 7	2.05	Accept (Poster)
1136	4.67	The Conditional Entropy Bottleneck	6, 2, 6	1.89	Reject
1137	4.67	Learning Information Propagation In The Dynamical Systems Via Information Bottleneck Hierarchy	5, 4, 5	0.47	Reject
1138	4.67	Partially Mutual Exclusive Softmax For Positive And Unlabeled Data	5, 4, 5	0.47	Reject
1139	4.67	Transfer Value Or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning	5, 4, 5	0.47	Reject
1140	4.67	Consistency-based Anomaly Detection With Adaptive Multiple-hypotheses Predictions	4, 5, 5	0.47	Reject
1141	4.67	Marginalized Average Attentional Network For Weakly-supervised Learning	5, 6, 3	1.25	Accept (Poster)
1142	4.67	Online Bellman Residue Minimization Via Saddle Point Optimization	5, 5, 4	0.47	N/A
1143	4.67	Object-oriented Model Learning Through Multi-level Abstraction	4, 4, 6	0.94	Reject
1144	4.67	Expressiveness In Deep Reinforcement Learning	6, 4, 4	0.94	Reject
1145	4.67	Scalable Neural Theorem Proving On Knowledge Bases And Natural Language	4, 5, 5	0.47	Reject
1146	4.50	Improving On-policy Learning With Statistical Reward Accumulation	4, 5	0.50	Reject
1147	4.50	Fast Binary Functional Search On Graph	4, 5	0.50	Reject
1148	4.50	One-shot High-fidelity Imitation: Training Large-scale Deep Nets With Rl	4, 4, 5, 5	0.50	Reject
1149	4.50	Online Abstraction With Mdp Homomorphisms For Deep Learning	4, 5	0.50	N/A
1150	4.50	Fast Exploration With Simplified Models And Approximately Optimistic Planning In Model Based Reinforcement Learning	5, 4	0.50	Reject
1151	4.50	Unification Of Recurrent Neural Network Architectures And Quantum Inspired Stable Design	5, 4, 4, 5	0.50	Reject
1152	4.40	Context Dependent Modulation Of Activation Function	4, 4, 4, 4, 6	0.80	Reject
1153	4.33	Multi-objective Value Iteration With Parameterized Threshold-based Safety Constraints	5, 5, 3	0.94	Reject
1154	4.33	Bridging Hmms And Rnns Through Architectural Transformations	5, 3, 5	0.94	N/A
1155	4.33	Learning Corresponded Rationales For Text Matching	6, 4, 3	1.25	Reject
1156	4.33	Modeling Dynamics Of Biological Systems With Deep Generative Neural Networks	6, 4, 3	1.25	Reject
1157	4.33	Learning Adversarial Examples With Riemannian Geometry	6, 4, 3	1.25	Reject
1158	4.33	Q-neurons: Neuron Activations Based On Stochastic Jackson's Derivative Operators	6, 2, 5	1.70	Reject
1159	4.33	From Nodes To Networks: Evolving Recurrent Neural Networks	5, 4, 4	0.47	Reject
1160	4.33	Combining Global Sparse Gradients With Local Gradients	5, 5, 3	0.94	N/A
1161	4.33	Efficient Sequence Labeling With Actor-critic Training	5, 4, 4	0.47	Reject
1162	4.33	Learning A Neural-network-based Representation For Open Set Recognition	4, 4, 5	0.47	Reject
1163	4.33	Mental Fatigue Monitoring Using Brain Dynamics Preferences	7, 4, 2	2.05	Reject
1164	4.33	Feed: Feature-level Ensemble Effect For Knowledge Distillation	5, 4, 4	0.47	Reject
1165	4.33	Pseudosaccades: A Simple Ensemble Scheme For Improving Classification Performance Of Deep Nets	5, 4, 4	0.47	Reject
1166	4.33	Unsupervised Meta-learning For Reinforcement Learning	3, 6, 4	1.25	Reject
1167	4.33	Total Style Transfer With A Single Feed-forward Network	4, 5, 4	0.47	Reject
1168	4.33	Pruning With Hints: An Efficient Framework For Model Acceleration	4, 5, 4	0.47	Reject
1169	4.33	Prototypical Examples In Deep Learning: Metrics, Characteristics, And Utility	3, 5, 5	0.94	Reject
1170	4.33	Classifier-agnostic Saliency Map Extraction	4, 5, 4	0.47	Reject
1171	4.33	A Guider Network For Multi-dual Learning	4, 5, 4	0.47	Reject
1172	4.33	Targeted Adversarial Examples For Black Box Audio Systems	4, 6, 3	1.25	Reject
1173	4.33	Meta-learning With Individualized Feature Space For Few-shot Classification	5, 5, 3	0.94	Reject
1174	4.33	Improving Sample-based Evaluation For Generative Adversarial Networks	5, 5, 3	0.94	Reject
1175	4.33	Variation Network: Learning High-level Attributes For Controlled Input Manipulation	3, 6, 4	1.25	Reject
1176	4.33	A Convergent Variant Of The Boltzmann Softmax Operator In Reinforcement Learning	4, 4, 5	0.47	Reject
1177	4.33	Variational Recurrent Models For Representation Learning	5, 3, 5	0.94	Reject
1178	4.33	The Natural Language Decathlon: Multitask Learning As Question Answering	5, 5, 3	0.94	Reject
1179	4.33	On The Effect Of The Activation Function On The Distribution Of Hidden Nodes In A Deep Network	4, 5, 4	0.47	Reject
1180	4.33	Variational Domain Adaptation	4, 4, 5	0.47	Reject
1181	4.33	Pixel Redrawn For A Robust Adversarial Defense	4, 6, 3	1.25	Reject
1182	4.33	Composition And Decomposition Of Gans	4, 5, 4	0.47	Reject
1183	4.33	Hiding Objects From Detectors: Exploring Transferrable Adversarial Patterns	6, 4, 3	1.25	N/A
1184	4.33	Representation Flow For Action Recognition	3, 5, 5	0.94	N/A
1185	4.33	Selective Self-training For Semi-supervised Learning	4, 5, 4	0.47	Reject
1186	4.33	Realistic Adversarial Examples In 3d Meshes	5, 5, 3	0.94	N/A
1187	4.33	Odin: Outlier Detection In Neural Networks	5, 4, 4	0.47	N/A
1188	4.33	Sense: Semantically Enhanced Node Sequence Embedding	4, 4, 5	0.47	Reject
1189	4.33	Label Smoothing And Logit Squeezing: A Replacement For Adversarial Training?	7, 4, 2	2.05	N/A
1190	4.33	Blackmarks: Black-box Multi-bit Watermarking For Deep Neural Networks	5, 4, 4	0.47	Reject
1191	4.33	Neural Probabilistic Motor Primitives For Humanoid Control	3, 6, 4	1.25	Accept (Poster)
1192	4.33	Compositional Gan: Learning Conditional Image Composition	4, 4, 5	0.47	N/A
1193	4.33	Representation Compression And Generalization In Deep Neural Networks	6, 3, 4	1.25	Reject
1194	4.33	Beyond Winning And Losing: Modeling Human Motivations And Behaviors With Vector-valued Inverse Reinforcement Learning	5, 4, 4	0.47	Reject
1195	4.33	Backdrop: Stochastic Backpropagation	5, 3, 5	0.94	Reject
1196	4.33	Contextualized Role Interaction For Neural Machine Translation	4, 5, 4	0.47	Reject
1197	4.33	Task-gan For Improved Gan Based Image Restoration	4, 5, 4	0.47	Reject
1198	4.33	Model-agnostic Meta-learning For Multimodal Task Distributions	3, 5, 5	0.94	Reject
1199	4.33	Stacked U-nets: A No-frills Approach To Natural Image Segmentation	5, 3, 5	0.94	N/A
1200	4.33	Unsupervised Classification Into Unknown Number Of Classes	4, 4, 5	0.47	Reject
1201	4.33	Fast Object Localization Via Sensitivity Analysis	4, 6, 3	1.25	Reject
1202	4.33	Variadic Learning By Bayesian Nonparametric Deep Embedding	5, 4, 4	0.47	Reject
1203	4.33	Asynchronous Sgd Without Gradient Delay For Efficient Distributed Training	5, 4, 4	0.47	Reject
1204	4.33	Shrinkage-based Bias-variance Trade-off For Deep Reinforcement Learning	4, 4, 5	0.47	Reject
1205	4.33	Unsupervised Latent Tree Induction With Deep Inside-outside Recursive Auto-encoders	5, 6, 2	1.70	N/A
1206	4.33	Low-cost Parameterizations Of Deep Convolutional Neural Networks	4, 4, 5	0.47	N/A
1207	4.33	Successor Uncertainties: Exploration And Uncertainty In Temporal Difference Learning	4, 5, 4	0.47	Reject
1208	4.33	End-to-end Hierarchical Text Classification With Label Assignment Policy	5, 4, 4	0.47	Reject
1209	4.33	Generalized Label Propagation Methods For Semi-supervised Learning	4, 3, 6	1.25	N/A
1210	4.33	Jumpout: Improved Dropout For Deep Neural Networks With Rectified Linear Units	5, 4, 4	0.47	Reject
1211	4.33	The Cakewalk Method	5, 4, 4	0.47	Reject
1212	4.33	W2gan: Recovering An Optimal Transport Map With A Gan	6, 3, 4	1.25	Reject
1213	4.33	Rating Continuous Actions In Spatial Multi-agent Problems	5, 4, 4	0.47	Reject
1214	4.33	Meta-learning To Guide Segmentation	7, 3, 3	1.89	Reject
1215	4.33	Stochastic Quantized Activation: To Prevent Overfitting In Fast Adversarial Training	4, 5, 4	0.47	Reject
1216	4.33	Dppnet: Approximating Determinantal Point Processes With Deep Networks	3, 5, 5	0.94	Reject
1217	4.33	Evolutionary-neural Hybrid Agents For Architecture Search	5, 4, 4	0.47	Reject
1218	4.33	Topicgan: Unsupervised Text Generation From Explainable Latent Topics	4, 4, 5	0.47	Reject
1219	4.33	Select Via Proxy: Efficient Data Selection For Training Deep Networks	4, 4, 5	0.47	Reject
1220	4.33	Deep Perm-set Net: Learn To Predict Sets With Unknown Permutation And Cardinality Using Deep Neural Networks	7, 3, 3	1.89	Reject
1221	4.33	In Your Pace: Learning The Right Example At The Right Time	5, 4, 4	0.47	Reject
1222	4.33	Modulating Transfer Between Tasks In Gradient-based Meta-learning	5, 4, 4	0.47	Reject
1223	4.33	A Preconditioned Accelerated Stochastic Gradient Descent Algorithm	4, 4, 5	0.47	Reject
1224	4.33	Adaptive Convolutional Neural Networks	5, 4, 4	0.47	Reject
1225	4.33	Inter-bmv: Interpolation With Block Motion Vectors For Fast Semantic Segmentation On Video	5, 3, 5	0.94	Reject
1226	4.33	Deeptwist: Learning Model Compression Via Occasional Weight Distortion	5, 4, 4	0.47	Reject
1227	4.33	Na	3, 5, 5	0.94	N/A
1228	4.33	N/a	5, 4, 4	0.47	N/A
1229	4.33	Generative Adversarial Interpolative Autoencoding: Adversarial Training On Latent Space Interpolations Encourages Convex Latent Distributions	5, 4, 4	0.47	Reject
1230	4.33	Aciq: Analytical Clipping For Integer Quantization Of Neural Networks	4, 4, 5	0.47	Reject
1231	4.33	Explainable Adversarial Learning: Implicit Generative Modeling Of Random Noise During Training For Adversarial Robustness	3, 5, 5	0.94	N/A
1232	4.33	Combining Learned Representations For Combinatorial Optimization	4, 4, 5	0.47	Reject
1233	4.33	Visual Imitation Learning With Recurrent Siamese Networks	4, 4, 5	0.47	Reject
1234	4.33	How To Learn (and How Not To Learn) Multi-hop Reasoning With Memory Networks	3, 5, 5	0.94	N/A
1235	4.33	Teaching To Teach By Structured Dark Knowledge	4, 3, 6	1.25	Reject
1236	4.33	Confidence Calibration In Deep Neural Networks Through Stochastic Inferences	5, 3, 5	0.94	N/A
1237	4.33	Isolating Effects Of Age With Fair Representation Learning When Assessing Dementia	4, 4, 5	0.47	N/A
1238	4.33	A Single Shot Pca-driven Analysis Of Network Structure To Remove Redundancy	4, 4, 5	0.47	N/A
1239	4.33	Learning To Control Visual Abstractions For Structured Exploration In Deep Reinforcement Learning	4, 5, 4	0.47	Reject
1240	4.33	Log Hyperbolic Cosine Loss Improves Variational Auto-encoder	4, 4, 5	0.47	Reject
1241	4.33	Locally Linear Unsupervised Feature Selection	4, 6, 3	1.25	Reject
1242	4.33	Sequence Modelling With Auto-addressing And Recurrent Memory Integrating Networks	4, 4, 5	0.47	Reject
1243	4.33	Learning What To Remember: Long-term Episodic Memory Networks For Learning From Streaming Data	5, 4, 4	0.47	Reject
1244	4.33	Universal Attacks On Equivariant Networks	4, 4, 5	0.47	Reject
1245	4.33	Incsql: Training Incremental Text-to-sql Parsers With Non-deterministic Oracles	4, 6, 3	1.25	N/A
1246	4.33	Provable Defenses Against Spatially Transformed Adversarial Inputs: Impossibility And Possibility Results	5, 3, 5	0.94	Reject
1247	4.33	Auto-encoding Knockoff Generator For Fdr Controlled Variable Selection	3, 4, 6	1.25	Reject
1248	4.33	Learning Grounded Sentence Representations By Jointly Using Video And Text Information	4, 3, 6	1.25	N/A
1249	4.33	Neural Rendering Model: Joint Generation And Prediction For Semi-supervised Learning	5, 5, 3	0.94	Reject
1250	4.33	Manifoldnet: A Deep Neural Network For Manifold-valued Data	5, 4, 4	0.47	Reject
1251	4.33	Unsupervised Word Discovery With Segmental Neural Language Models	4, 3, 6	1.25	Reject
1252	4.33	Network Reparameterization For Unseen Class Categorization	5, 3, 5	0.94	N/A
1253	4.33	Deep Geometrical Graph Classification	4, 3, 6	1.25	Reject
1254	4.33	Generative Models From The Perspective Of Continual Learning	4, 5, 4	0.47	Reject
1255	4.33	Adversarial Examples Are A Natural Consequence Of Test Error In Noise	4, 5, 4	0.47	Reject
1256	4.33	Wasserstein Proximal Of Gans	3, 6, 4	1.25	Reject
1257	4.33	From Adversarial Training To Generative Adversarial Networks	3, 6, 4	1.25	N/A
1258	4.33	Adversarial Decomposition Of Text Representation	3, 6, 4	1.25	N/A
1259	4.33	Neuron Hierarchical Networks	5, 4, 4	0.47	N/A
1260	4.33	Sample Efficient Deep Neuroevolution In Low Dimensional Latent Space	4, 5, 4	0.47	Reject
1261	4.33	Downsampling Leads To Image Memorization In Convolutional Autoencoders	3, 5, 5	0.94	Reject
1262	4.33	Online Learning For Supervised Dimension Reduction	2, 5, 6	1.70	Reject
1263	4.33	Nice: Noise Injection And Clamping Estimation For Neural Network Quantization	4, 5, 4	0.47	Reject
1264	4.33	Assessing Generalization In Deep Reinforcement Learning	3, 5, 5	0.94	Reject
1265	4.33	Do Language Models Have Common Sense?	5, 4, 4	0.47	Reject
1266	4.33	Efficient Convolutional Neural Network Training With Direct Feedback Alignment	4, 4, 5	0.47	Reject
1267	4.33	Q-map: A Convolutional Approach For Goal-oriented Reinforcement Learning	5, 4, 4	0.47	Reject
1268	4.33	Deep Ensemble Bayesian Active Learning : Adressing The Mode Collapse Issue In Monte Carlo Dropout Via Ensembles	4, 4, 5	0.47	Reject
1269	4.33	Salsa-text : Self Attentive Latent Space Based Adversarial Text Generation	4, 4, 5	0.47	N/A
1270	4.33	Pie: Pseudo-invertible Encoder	3, 5, 5	0.94	Reject
1271	4.33	On Inductive Biases In Deep Reinforcement Learning	3, 3, 7	1.89	Reject
1272	4.33	Na	5, 4, 4	0.47	N/A
1273	4.33	Dvolver: Efficient Pareto-optimal Neural Network Architecture Search	4, 5, 4	0.47	Reject
1274	4.33	Dual Learning: Theoretical Study And Algorithmic Extensions	6, 2, 5	1.70	Reject
1275	4.33	Gradient-based Learning For F-measure And Other Performance Metrics	5, 3, 5	0.94	Reject
1276	4.33	Robust Text Classifier On Test-time Budgets	4, 4, 5	0.47	N/A
1277	4.33	Recycling The Discriminator For Improving The Inference Mapping Of Gan	3, 3, 7	1.89	Reject
1278	4.33	Shamann: Shared Memory Augmented Neural Networks	4, 5, 4	0.47	Reject
1279	4.33	Recovering The Lowest Layer Of Deep Networks With High Threshold Activations	4, 5, 4	0.47	Reject
1280	4.33	Exploration By Uncertainty In Reward Space	5, 5, 3	0.94	Reject
1281	4.33	Modulated Variational Auto-encoders For Many-to-many Musical Timbre Transfer	5, 5, 3	0.94	Reject
1282	4.33	On Generalization Bounds Of A Family Of Recurrent Neural Networks	4, 6, 3	1.25	Reject
1283	4.33	Feature Matters: A Stage-by-stage Approach For Task Independent Knowledge Transfer	5, 4, 4	0.47	N/A
1284	4.33	Sentence Encoding With Tree-constrained Relation Networks	3, 5, 5	0.94	Reject
1285	4.25	A Priori Estimates Of The Generalization Error For Two-layer Neural Networks	4, 4, 4, 5	0.43	Reject
1286	4.25	Understanding The Asymptotic Performance Of Model-based Rl Methods	5, 6, 4, 2	1.48	Reject
1287	4.25	Discovering General-purpose Active Learning Strategies	5, 4, 4, 4	0.43	Reject
1288	4.25	On Meaning-preserving Adversarial Perturbations For Sequence-to-sequence Models	4, 4, 3, 6	1.09	Reject
1289	4.25	Characterizing The Accuracy/complexity Landscape Of Explanations Of Deep Networks Through Knowledge Extraction	4, 4, 4, 5	0.43	Reject
1290	4.25	Countdown Regression: Sharp And Calibrated Survival Predictions	4, 4, 4, 5	0.43	Reject
1291	4.00	Neural Regression Tree	5, 3, 4	0.82	Reject
1292	4.00	The Effectiveness Of Layer-by-layer Training Using The Information Bottleneck Principle	5, 2, 5	1.41	Reject
1293	4.00	S-system, Geometry, Learning, And Optimization: A Theory Of Neural Networks	4, 4	0.00	Reject
1294	4.00	Learning Latent Semantic Representation From Pre-defined Generative Model	5, 3, 4	0.82	Reject
1295	4.00	Fatty And Skinny: A Joint Training Method Of Watermark Encoder And Decoder	4, 4, 4	0.00	N/A
1296	4.00	Reconciling Feature-reuse And Overfitting In Densenet With Specialized Dropout	5, 3, 4	0.82	Reject
1297	4.00	Functional Bayesian Neural Networks For Model Uncertainty Quantification	3, 4, 5	0.82	Reject
1298	4.00	Empirically Characterizing Overparameterization Impact On Convergence	5, 4, 3	0.82	Reject
1299	4.00	Exploration Using Distributional Rl And Ucb	4, 4, 4	0.00	N/A
1300	4.00	Revisting Negative Transfer Using Adversarial Learning	4, 2, 6	1.63	Reject
1301	4.00	Distilled Agent Dqn For Provable Adversarial Robustness	5, 3, 4	0.82	Reject
1302	4.00	Reinforced Pipeline Optimization: Behaving Optimally With Non-differentiabilities	4, 5, 3	0.82	Reject
1303	4.00	Generalized Capsule Networks With Trainable Routing Procedure	5, 3, 4	0.82	Reject
1304	4.00	Learning From Noisy Demonstration Sets Via Meta-learned Suitability Assessor	4, 4, 4	0.00	Reject
1305	4.00	Latent Domain Transfer: Crossing Modalities With Bridging Autoencoders	4, 4, 4	0.00	Reject
1306	4.00	Complexity Of Training Relu Neural Networks	3, 5, 4	0.82	Reject
1307	4.00	Learning To Search Efficient Densenet With Layer-wise Pruning	4, 4, 4	0.00	Reject
1308	4.00	Conditional Inference In Pre-trained Variational Autoencoders Via Cross-coding	4, 4, 4	0.00	Reject
1309	4.00	The Wisdom Of The Crowd: Reliable Deep Reinforcement Learning Through Ensembles Of Q-functions	4, 5, 3	0.82	Reject
1310	4.00	Guaranteed Recovery Of One-hidden-layer Neural Networks Via Cross Entropy	3, 4, 5	0.82	Reject
1311	4.00	D2ke: From Distance To Kernel And Embedding Via Random Features For Structured Inputs	4, 3, 5	0.82	N/A
1312	4.00	Graph Generation Via Scattering	4, 4, 4	0.00	Reject
1313	4.00	Classification Of Building Noise Type/position Via Supervised Learning	4, 4, 4	0.00	N/A
1314	4.00	Explaining Neural Networks Semantically And Quantitatively	4, 4, 4	0.00	N/A
1315	4.00	Look Ma, No Gans! Image Transformation With Modifae	3, 4, 5	0.82	Reject
1316	4.00	The Forward-backward Embedding Of Directed Graphs	5, 3, 4	0.82	Reject
1317	4.00	Efficient Exploration Through Bayesian Deep Q-networks	6, 4, 4, 2	1.41	Reject
1318	4.00	Hc-net: Memory-based Incremental Dual-network System For Continual Learning	4, 4, 4	0.00	Reject
1319	4.00	Multi-task Learning For Semantic Parsing With Cross-domain Sketch	3, 4, 5	0.82	Reject
1320	4.00	Rnns With Private And Shared Representations For Semi-supervised Sequence Learning	3, 5, 4	0.82	N/A
1321	4.00	Na	6, 2, 4	1.63	N/A
1322	4.00	The Missing Ingredient In Zero-shot Neural Machine Translation	5, 4, 3	0.82	N/A
1323	4.00	Evading Defenses To Transferable Adversarial Examples By Mitigating Attention Shift	4, 4, 4	0.00	N/A
1324	4.00	Applications Of Gaussian Processes In Finance	4, 5, 3	0.82	N/A
1325	4.00	Evaluating Gans Via Duality	4, 3, 5	0.82	Reject
1326	4.00	Neural Network Cost Landscapes As Quantum States	5, 3, 4	0.82	Reject
1327	4.00	Deep Adversarial Forward Model	4, 4, 4	0.00	Reject
1328	4.00	In Search Of Theoretically Grounded Pruning	4, 3, 5	0.82	N/A
1329	4.00	Mol-cyclegan - A Generative Model For Molecular Optimization	4, 4, 4	0.00	Reject
1330	4.00	Overlapping Community Detection With Graph Neural Networks	5, 3, 4	0.82	Reject
1331	4.00	Chaingan: A Sequential Approach To Gans	4, 4, 4	0.00	Reject
1332	4.00	Constraining Action Sequences With Formal Languages For Deep Reinforcement Learning	5, 3, 4	0.82	Reject
1333	4.00	Trajectory Vae For Multi-modal Imitation	4, 4, 4	0.00	Reject
1334	4.00	Improving Machine Classification Using Human Uncertainty Measurements	6, 3, 3	1.41	Reject
1335	4.00	Differentially Private Federated Learning: A Client Level Perspective	4, 4, 4	0.00	Reject
1336	4.00	N/a	4, 5, 3	0.82	N/A
1337	4.00	Exploiting Invariant Structures For Compression In Neural Networks	4, 4, 4	0.00	N/A
1338	4.00	Continual Learning Via Explicit Structure Learning	4, 4, 4	0.00	Reject
1339	4.00	Difference-seeking Generative Adversarial Network	5, 4, 3	0.82	Reject
1340	4.00	Assumption Questioning: Latent Copying And Reward Exploitation In Question Generation	4, 3, 5	0.82	Reject
1341	4.00	Second-order Adversarial Attack And Certifiable Robustness	4, 5, 3	0.82	Reject
1342	4.00	A Multi-modal One-class Generative Adversarial Network For Anomaly Detection In Manufacturing	3, 4, 5	0.82	Reject
1343	4.00	Deep Generative Models For Learning Coherent Latent Representations From Multi-modal Data	4, 4, 4	0.00	Reject
1344	4.00	Sequenced-replacement Sampling For Deep Learning	3, 5, 4	0.82	Reject
1345	4.00	Sample-efficient Policy Learning In Multi-agent Reinforcement Learning Via Meta-learning	4, 4, 4	0.00	Reject
1346	4.00	Overfitting Detection Of Deep Neural Networks Without A Hold Out Set	4, 5, 3	0.82	Reject
1347	4.00	On The Selection Of Initialization And Activation Function For Deep Neural Networks	3, 4, 5	0.82	Reject
1348	4.00	Constrained Bayesian Optimization For Automatic Chemical Design	3, 4, 5	0.82	Reject
1349	4.00	Dual Importance Weight Gan	4, 3, 5	0.82	N/A
1350	4.00	Robustness And Equivariance Of Neural Networks	3, 4, 5	0.82	Reject
1351	4.00	Incremental Hierarchical Reinforcement Learning With Multitask Lmdps	3, 4, 5	0.82	Reject
1352	4.00	Cosine Similarity-based Adversarial Process	4, 3, 5	0.82	N/A
1353	4.00	Training Hard-threshold Networks With Combinatorial Search In A Discrete Target Propagation Setting	3, 4, 5	0.82	Reject
1354	4.00	On The Use Of Convolutional Auto-encoder For Incremental Classifier Learning In Context Aware Advertisement	5, 4, 3	0.82	Reject
1355	4.00	Exploration Of Efficient On-device Acoustic Modeling With Neural Networks	4, 4, 4	0.00	Reject
1356	4.00	Microgan: Promoting Variety Through Microbatch Discrimination	3, 3, 6	1.41	Reject
1357	4.00	Better Accuracy With Quantified Privacy: Representations Learned Via Reconstructive Adversarial Network	4, 5, 3	0.82	Reject
1358	4.00	Merci: A New Metric To Evaluate The Correlation Between Predictive Uncertainty And True Error	4, 5, 3	0.82	Reject
1359	4.00	Deep Processing Of Structured Data	4, 4, 4	0.00	Reject
1360	4.00	Iterative Binary Decisions	4, 4, 4	0.00	N/A
1361	4.00	Understanding Opportunities For Efficiency In Single-image Super Resolution Networks	4, 5, 3	0.82	Reject
1362	4.00	Unsupervised Convolutional Neural Networks For Accurate Video Frame Interpolation With Integration Of Motion Components	3, 5, 4	0.82	N/A
1363	4.00	Learning Representations In Model-free Hierarchical Reinforcement Learning	5, 4, 3	0.82	Reject
1364	4.00	Accidental Exploration Through Value Predictors	4, 5, 3	0.82	Reject
1365	4.00	Language Modeling With Graph Temporal Convolutional Networks	4, 4, 4	0.00	Reject
1366	4.00	Overcoming Catastrophic Forgetting Through Weight Consolidation And Long-term Memory	4, 4, 4	0.00	Reject
1367	4.00	Modular Deep Probabilistic Programming	3, 4, 5	0.82	Reject
1368	4.00	Relational Graph Attention Networks	4, 4, 4	0.00	Reject
1369	4.00	Towards More Theoretically-grounded Particle Optimization Sampling For Deep Learning	5, 4, 3	0.82	Reject
1370	4.00	Layerwise Recurrent Autoencoder For General Real-world Traffic Flow Forecasting	4, 5, 3	0.82	Reject
1371	4.00	Activity Regularization For Continual Learning	4, 4, 4	0.00	Reject
1372	4.00	Dynamic Pricing On E-commerce Platform With Deep Reinforcement Learning	4, 4, 4	0.00	Reject
1373	4.00	Defactor: Differentiable Edge Factorization-based Probabilistic Graph Generation	3, 5, 4	0.82	Reject
1374	4.00	Data Poisoning Attack Against Unsupervised Node Embedding Methods	4, 4, 4	0.00	N/A
1375	4.00	Distributionally Robust Optimization Leads To Better Generalization: On Sgd And Beyond	3, 4, 5	0.82	Reject
1376	4.00	Uainets: From Unsupervised To Active Deep Anomaly Detection	4, 5, 3	0.82	Reject
1377	4.00	Implicit Maximum Likelihood Estimation	4, 3, 5	0.82	Reject
1378	4.00	Prob2vec: Mathematical Semantic Embedding For Problem Retrieval In Adaptive Tutoring	3, 5, 4	0.82	Reject
1379	4.00	Hyper-regularization: An Adaptive Choice For The Learning Rate In Gradient Descent	4, 4, 4	0.00	Reject
1380	4.00	A Teacher Student Network For Faster Video Classification	4, 4, 4	0.00	N/A
1381	4.00	Deepström Networks	4, 5, 3	0.82	N/A
1382	4.00	Universal Discriminative Quantum Neural Networks	5, 5, 2	1.41	Reject
1383	4.00	Morpho-mnist: Quantitative Assessment And Diagnostics For Representation Learning	3, 5, 4	0.82	Reject
1384	4.00	Uncertainty-guided Lifelong Learning In Bayesian Networks	4, 4, 4	0.00	Reject
1385	4.00	Distinguishability Of Adversarial Examples	4, 4, 4	0.00	Reject
1386	4.00	Pearl: Prototype Learning Via Rule Lists	5, 3, 4	0.82	Reject
1387	4.00	Nuts: Network For Unsupervised Telegraphic Summarization	4, 4, 4	0.00	Reject
1388	4.00	Unsupervised Exploration With Deep Model-based Reinforcement Learning	4, 4, 4	0.00	Reject
1389	4.00	Adversarial Attacks For Optical Flow-based Action Recognition Classifiers	4, 3, 5	0.82	Reject
1390	4.00	Found By Nemo: Unsupervised Object Detection From Negative Examples And Motion	5, 3, 4	0.82	N/A
1391	4.00	On The Statistical And Information Theoretical Characteristics Of Dnn Representations	5, 4, 3	0.82	Reject
1392	4.00	Decoupling Feature Extraction From Policy Learning: Assessing Benefits Of State Representation Learning In Goal Based Robotics	5, 3, 4	0.82	Reject
1393	4.00	Ain't Nobody Got Time For Coding: Structure-aware Program Synthesis From Natural Language	4, 4, 4	0.00	Reject
1394	4.00	On The Trajectory Of Stochastic Gradient Descent In The Information Plane	4, 6, 2	1.63	Reject
1395	4.00	Polar Prototype Networks	5, 3, 4	0.82	Reject
1396	3.75	The Body Is Not A Given: Joint Agent Policy Learning And Morphology Evolution	4, 4, 3, 4	0.43	N/A
1397	3.75	Lsh Microbatches For Stochastic Gradients: Value In Rearrangement	4, 4, 3, 4	0.43	Reject
1398	3.67	Fake Sentence Detection As A Training Task For Sentence Encoding	5, 3, 3	0.94	Reject
1399	3.67	Inhibited Softmax For Uncertainty Estimation In Neural Networks	4, 4, 3	0.47	N/A
1400	3.67	Parametrizing Fully Convolutional Nets With A Single High-order Tensor	4, 3, 4	0.47	N/A
1401	3.67	A Walk With Sgd: How Sgd Explores Regions Of Deep Network Loss?	4, 4, 3	0.47	Reject
1402	3.67	Interpretable Convolutional Filter Pruning	4, 4, 3	0.47	Reject
1403	3.67	A Fully Automated Periodicity Detection In Time Series	3, 5, 3	0.94	Reject
1404	3.67	Geometric Augmentation For Robust Neural Network Classifiers	4, 4, 3	0.47	Reject
1405	3.67	Optimized Gated Deep Learning Architectures For Sensor Fusion	4, 4, 3	0.47	Reject
1406	3.67	Graph Spectral Regularization For Neural Network Interpretability	4, 3, 4	0.47	Reject
1407	3.67	Synthnet: Learning Synthesizers End-to-end	4, 4, 3	0.47	Reject
1408	3.67	Question Generation Using A Scratchpad Encoder	4, 3, 4	0.47	Reject
1409	3.67	Spectral Convolutional Networks On Hierarchical Multigraphs	4, 3, 4	0.47	N/A
1410	3.67	Feature Transformers: A Unified Representation Learning Framework For Lifelong Learning	4, 3, 4	0.47	Reject
1411	3.67	Learning Robust, Transferable Sentence Representations For Text Classification	4, 3, 4	0.47	N/A
1412	3.67	Using Deep Siamese Neural Networks To Speed Up Natural Products Research	4, 3, 4	0.47	Reject
1413	3.67	Unsupervised Video-to-video Translation	3, 4, 4	0.47	Reject
1414	3.67	Bilingual-gan: Neural Text Generation And Neural Machine Translation As Two Sides Of The Same Coin	3, 4, 4	0.47	N/A
1415	3.67	Optimizing For Generalization In Machine Learning With Cross-validation Gradients	5, 2, 4	1.25	Reject
1416	3.67	Radial Basis Feature Transformation To Arm Cnns Against Adversarial Attacks	4, 4, 3	0.47	Reject
1417	3.67	Feature Attribution As Feature Selection	4, 4, 3	0.47	Reject
1418	3.67	Filter Training And Maximum Response: Classification Via Discerning	2, 3, 6	1.70	Reject
1419	3.67	Unsupervised Monocular Depth Estimation With Clear Boundaries	4, 4, 3	0.47	N/A
1420	3.67	Beyond Games: Bringing Exploration To Robots In Real-world	3, 3, 5	0.94	Reject
1421	3.67	Withdrawn	4, 4, 3	0.47	N/A
1422	3.67	Prior Networks For Detection Of Adversarial Attacks	3, 4, 4	0.47	Reject
1423	3.67	Accelerating First Order Optimization Algorithms	3, 4, 4	0.47	Reject
1424	3.67	Mixture Of Pre-processing Experts Model For Noise Robust Deep Learning On Resource Constrained Platforms	3, 4, 4	0.47	Reject
1425	3.67	Text Embeddings For Retrieval From A Large Knowledge Base	3, 3, 5	0.94	Reject
1426	3.67	Discrete Structural Planning For Generating Diverse Translations	2, 4, 5	1.25	Reject
1427	3.67	Structured Prediction Using Cgans With Fusion Discriminator	5, 3, 3	0.94	Reject
1428	3.67	Na	4, 4, 3	0.47	N/A
1429	3.67	Normalization Gradients Are Least-squares Residuals	4, 4, 3	0.47	Reject
1430	3.67	Deep Hierarchical Model For Hierarchical Selective Classification And Zero Shot Learning	4, 5, 2	1.25	Reject
1431	3.67	Graph Learning Network: A Structure Learning Algorithm	4, 3, 4	0.47	Reject
1432	3.67	Quantile Regression Reinforcement Learning With State Aligned Vector Rewards	4, 3, 4	0.47	N/A
1433	3.67	Towards The Latent Transcriptome	4, 2, 5	1.25	Reject
1434	3.67	Explaining Alphago: Interpreting Contextual Effects In Neural Networks	3, 4, 4	0.47	N/A
1435	3.67	Dyncnn: An Effective Dynamic Architecture On Convolutional Neural Network For Surveillance Videos	3, 4, 4	0.47	Reject
1436	3.67	D-gan: Divergent Generative Adversarial Network For Positive Unlabeled Learning And Counter-examples Generation	3, 5, 3	0.94	Reject
1437	3.67	Using Word Embeddings To Explore The Learned Representations Of Convolutional Neural Networks	3, 4, 4	0.47	Reject
1438	3.67	Automatic Generation Of Object Shapes With Desired Functionalities	5, 3, 3	0.94	Reject
1439	3.67	Delibgan: Coarse-to-fine Text Generation Via Adversarial Network	4, 3, 4	0.47	Reject
1440	3.67	Rethinking Self-driving : Multi -task Knowledge For Better Generalization And Accident Explanation Ability	4, 4, 3	0.47	Reject
1441	3.67	Gradmix: Multi-source Transfer Across Domains And Tasks	5, 3, 3	0.94	N/A
1442	3.67	Polycnn: Learning Seed Convolutional Filters	3, 4, 4	0.47	N/A
1443	3.67	Why Do Neural Response Generation Models Prefer Universal Replies?	3, 7, 1	2.49	Reject
1444	3.67	Residual Networks Classify Inputs Based On Their Neural Transient Dynamics	4, 2, 5	1.25	Reject
1445	3.67	Object-contrastive Networks: Unsupervised Object Representations	3, 3, 5	0.94	N/A
1446	3.67	Latent Transformations For Object View Points Synthesis	2, 4, 5	1.25	N/A
1447	3.67	An Attention-based Model For Learning Dynamic Interaction Networks	4, 3, 4	0.47	N/A
1448	3.67	Hierarchical Attention: What Really Counts In Various Nlp Tasks	4, 3, 4	0.47	Reject
1449	3.67	Modeling Evolution Of Language Through Time With Neural Networks	3, 4, 4	0.47	N/A
1450	3.67	Contextual Recurrent Convolutional Model For Robust Visual Learning	4, 3, 4	0.47	Reject
1451	3.67	Generating Images From Sounds Using Multimodal Features And Gans	3, 4, 4	0.47	Reject
1452	3.67	Differentiable Greedy Networks	5, 2, 4	1.25	N/A
1453	3.67	Learning Agents With Prioritization And Parameter Noise In Continuous State And Action Space	3, 4, 4	0.47	Reject
1454	3.67	Optimization On Multiple Manifolds	7, 1, 3	2.49	Reject
1455	3.67	Unsupervised One-to-many Image Translation	3, 4, 4	0.47	Reject
1456	3.67	Adversarially Robust Training Through Structured Gradient Regularization	4, 4, 3	0.47	Reject
1457	3.67	Distributed Deep Policy Gradient For Competitive Adversarial Environment	4, 4, 3	0.47	N/A
1458	3.67	Diminishing Batch Normalization	4, 3, 4	0.47	Reject
1459	3.67	Efficient Federated Learning Via Variational Dropout	4, 4, 3	0.47	N/A
1460	3.67	Pcnn: Environment Adaptive Model Without Finetuning	4, 3, 4	0.47	Reject
1461	3.67	Localized Random Projections Challenge Benchmarks For Bio-plausible Deep Learning	5, 3, 3	0.94	Reject
1462	3.67	Riemannian Stochastic Gradient Descent For Tensor-train Recurrent Neural Networks	4, 4, 3	0.47	Reject
1463	3.67	Imposing Category Trees Onto Word-embeddings Using A Geometric Construction	4, 4, 3	0.47	Accept (Poster)
1464	3.67	Few-shot Intent Inference Via Meta-inverse Reinforcement Learning	3, 4, 4	0.47	Reject
1465	3.67	Controlling Over-generalization And Its Effect On Adversarial Examples Detection And Generation	4, 4, 3	0.47	Reject
1466	3.67	Image Score: How To Select Useful Samples	4, 4, 3	0.47	Reject
1467	3.50	Bamboo: Ball-shape Data Augmentation Against Adversarial Attacks From All Directions	4, 3	0.50	N/A
1468	3.50	Learning To Reinforcement Learn By Imitation	4, 3, 2, 5	1.12	Reject
1469	3.50	Mctsbug: Generating Adversarial Text Sequences Via Monte Carlo Tree Search And Homoglyph Attack	3, 4	0.50	N/A
1470	3.33	Major-minor Lstms For Word-level Language Model	3, 4, 3	0.47	N/A
1471	3.33	Human Action Recognition Based On Spatial-temporal Attention	4, 3, 3	0.47	Reject
1472	3.33	Generative Model Based On Minimizing Exact Empirical Wasserstein Distance	5, 2, 3	1.25	Reject
1473	3.33	Neural Network Regression With Beta, Dirichlet, And Dirichlet-multinomial Outputs	3, 3, 4	0.47	Reject
1474	3.33	A Quantifiable Testing Of Global Translational Invariance In Convolutional And Capsule Networks	3, 4, 3	0.47	Reject
1475	3.33	Na	4, 5, 1	1.70	N/A
1476	3.33	Interpreting Layered Neural Networks Via Hierarchical Modular Representation	4, 3, 3	0.47	Reject
1477	3.33	Attack Graph Convolutional Networks By Adding Fake Nodes	4, 3, 3	0.47	Reject
1478	3.33	Visualizing And Understanding The Semantics Of Embedding Spaces Via Algebraic Formulae	3, 3, 4	0.47	Reject
1479	3.33	Combining Adaptive Algorithms And Hypergradient Method: A Performance And Robustness Study	3, 3, 4	0.47	Reject
1480	3.33	Logit Regularization Methods For Adversarial Robustness	3, 5, 2	1.25	N/A
1481	3.33	Linearizing Visual Processes With Deep Generative Models	3, 3, 4	0.47	N/A
1482	3.33	Associate Normalization	3, 5, 2	1.25	N/A
1483	3.33	Understanding And Improving Sequence-labeling Ner With Self-attentive Lstms	3, 3, 4	0.47	N/A
1484	3.33	Step-wise Sensitivity Analysis: Identifying Partially Distributed Representations For Interpretable Deep Learning	3, 4, 3	0.47	Reject
1485	3.33	Bigsage: Unsupervised Inductive Representation Learning Of Graph Via Bi-attended Sampling And Global-biased Aggregating	2, 4, 4	0.94	Reject
1486	3.33	Learning Spatio-temporal Representations Using Spike-based Backpropagation	3, 4, 3	0.47	N/A
1487	3.33	Featurized Bidirectional Gan: Adversarial Defense Via Adversarially Learned Semantic Inference	3, 4, 3	0.47	Reject
1488	3.33	Iea: Inner Ensemble Average Within A Convolutional Neural Network	4, 2, 4	0.94	Reject
1489	3.33	Geometric Operator Convolutional Neural Network	2, 5, 3	1.25	N/A
1490	3.33	Neural Random Projections For Language Modelling	3, 4, 3	0.47	Reject
1491	3.33	Empirical Study Of Easy And Hard Examples In Cnn Training	3, 4, 3	0.47	Reject
1492	3.33	Large-scale Classification Of Structured Objects Using A Crf With Deep Class Embedding	3, 3, 4	0.47	Reject
1493	3.33	Non-synergistic Variational Autoencoders	3, 4, 3	0.47	Reject
1494	3.33	Detecting Topological Defects In 2d Active Nematics Using Convolutional Neural Networks	4, 4, 2	0.94	Reject
1495	3.33	Deconfounding Reinforcement Learning In Observational Settings	4, 4, 2	0.94	Reject
1496	3.33	Learning Powerful Policies And Better Dynamics Models By Encouraging Consistency	3, 2, 5	1.25	Reject
1497	3.33	Offline Deep Models Calibration With Bayesian Neural Networks	4, 3, 3	0.47	Reject
1498	3.33	She2: Stochastic Hamiltonian Exploration And Exploitation For Derivative-free Optimization	4, 3, 3	0.47	Reject
1499	3.33	Gradient Acceleration In Activation Functions	5, 2, 3	1.25	Reject
1500	3.33	Behavior Module In Neural Networks	3, 3, 4	0.47	Reject
1501	3.33	Learning And Data Selection In Big Datasets	4, 3, 3	0.47	N/A
1502	3.33	Multi-scale Stacked Hourglass Network For Human Pose Estimation	3, 4, 3	0.47	Reject
1503	3.33	Neural Distribution Learning For Generalized Time-to-event Prediction	4, 3, 3	0.47	Reject
1504	3.33	Encoder Discriminator Networks For Unsupervised Representation Learning	3, 4, 3	0.47	N/A
1505	3.00	Hr-td: A Regularized Td Method To Avoid Over-generalization	4, 3, 2	0.82	Reject
1506	3.00	Spamhmm: Sparse Mixture Of Hidden Markov Models For Graph Connected Entities	3, 3, 3	0.00	N/A
1507	3.00	Real-time Neural-based Input Method	3, 3, 3	0.00	Reject
1508	3.00	Learn From Neighbour: A Curriculum That Train Low Weighted Samples By Imitating	2, 3, 4	0.82	Reject
1509	3.00	Variational Autoencoders For Text Modeling Without Weakening The Decoder	4, 1, 4	1.41	N/A
1510	3.00	An Exhaustive Analysis Of Lazy Vs. Eager Learning Methods For Real-estate Property Investment	3, 4, 2	0.82	Reject
1511	3.00	A Non-linear Theory For Sentence Embedding	3, 3, 3	0.00	Reject
1512	3.00	Geometry Of Deep Convolutional Networks	2, 4, 3	0.82	N/A
1513	3.00	Probabilistic Program Induction For Intuitive Physics Game Play	3, 4, 2	0.82	Reject
1514	3.00	A Self-supervised Method For Mapping Human Instructions To Robot Policies	4, 3, 2	0.82	Reject
1515	3.00	Mapping The Hyponymy Relation Of Wordnet Onto Vector Spaces	3, 3, 3	0.00	Reject
1516	3.00	Learning With Reflective Likelihoods	4, 2, 3	0.82	Reject
1517	3.00	Attentive Explainability For Patient Temporal Embedding	4, 3, 2	0.82	Reject
1518	3.00	Generative Model For Material Irradiation Experiments Based On Prior Knowledge And Attention Mechanism	3, 3	0.00	N/A
1519	3.00	An Analysis Of Composite Neural Network Performance From Function Composition Perspective	3, 3, 3	0.00	Reject
1520	3.00	A Forensic Representation To Detect Non-trivial Image Duplicates, And How It Applies To Semantic Segmentation	4, 3, 2	0.82	N/A
1521	3.00	Calibration Of Neural Network Logit Vectors To Combat Adversarial Attacks	3, 2, 4	0.82	Reject
1522	3.00	Handling Concept Drift In Wifi-based Indoor Localization Using Representation Learning	2, 3, 4	0.82	N/A
1523	3.00	Classification In The Dark Using Tactile Exploration	4, 3, 2	0.82	Reject
1524	3.00	End-to-end Multi-lingual Multi-speaker Speech Recognition	3, 3, 3	0.00	Reject
1525	3.00	Nonlinear Channels Aggregation Networks For Deep Action Recognition	3, 3, 3	0.00	N/A
1526	3.00	From Amortised To Memoised Inference: Combining Wake-sleep And Variational-bayes For Unsupervised Few-shot Program Learning	3, 3, 3	0.00	N/A
1527	3.00	Dopamine: A Research Framework For Deep Reinforcement Learning	3, 3, 3	0.00	Reject
1528	3.00	Hybrid Policies Using Inverse Rewards For Reinforcement Learning	3, 2, 4	0.82	Reject
1529	3.00	From Deep Learning To Deep Deducing: Automatically Tracking Down Nash Equilibrium Through Autonomous Neural Agent, A Possible Missing Step Toward General A.i.	3, 2, 4	0.82	Reject
1530	3.00	Uncertainty In Multitask Transfer Learning	3, 2, 4	0.82	Reject
1531	3.00	Reneg And Backseat Driver: Learning From Demonstration With Continuous Human Feedback	3, 4, 2	0.82	Reject
1532	3.00	A Rate-distortion Theory Of Adversarial Examples	4, 3, 2	0.82	Reject
1533	3.00	Attention Incorporate Network: A Network Can Adapt Various Data Size	3, 4, 2	0.82	Reject
1534	3.00	Learning Of Sophisticated Curriculums By Viewing Them As Graphs Over Tasks	3, 2, 4	0.82	N/A
1535	3.00	Irda Method For Sparse Convolutional Neural Networks	3, 3, 3	0.00	Reject
1536	3.00	Evaluation Methodology For Attacks Against Confidence Thresholding Models	2, 3, 4	0.82	Reject
1537	3.00	Feature Quantization For Parsimonious And Interpretable Predictive Models	2, 3, 4	0.82	Reject
1538	3.00	Stacking For Transfer Learning	3, 4, 2	0.82	Reject
1539	3.00	One Bit Matters: Understanding Adversarial Examples As The Abuse Of Redundancy	3, 3, 3	0.00	N/A
1540	3.00	Knowledge Distill Via Learning Neuron Manifold	5, 1, 3	1.63	N/A
1541	2.75	Predictive Local Smoothness For Stochastic Gradient Methods	2, 3, 2, 4	0.83	Reject
1542	2.67	Variational Sgd: Dropout , Generalization And Critical Point At The End Of Convexity	4, 2, 2	0.94	Reject
1543	2.67	Weak Contraction Mapping And Optimization	3, 1, 4	1.25	Reject
1544	2.67	Learning Goal-conditioned Value Functions With One-step Path Rewards Rather Than Goal-rewards	4, 1, 3	1.25	Reject
1545	2.67	Multiple Encoder-decoders Net For Lane Detection	2, 2, 4	0.94	Reject
1546	2.67	Explaining Adversarial Examples With Knowledge Representation	3, 3, 2	0.47	Reject
1547	2.67	End-to-end Learning Of Video Compression Using Spatio-temporal Autoencoders	3, 3, 2	0.47	Reject
1548	2.67	A Case Study On Optimal Deep Learning Model For Uavs	3, 3, 2	0.47	Reject
1549	2.67	Decoupling Gating From Linearity	3, 2, 3	0.47	Reject
1550	2.67	Happier: Hierarchical Polyphonic Music Generative Rnn	2, 3, 3	0.47	Reject
1551	2.67	Faster Training By Selecting Samples Using Embeddings	3, 3, 2	0.47	Reject
1552	2.67	A Bird's Eye View On Coherence, And A Worm's Eye View On Cohesion	2, 2, 4	0.94	Reject
1553	2.67	Exponentially Decaying Flows For Optimization In Deep Learning	3, 3, 2	0.47	N/A
1554	2.50	A Solution To China Competitive Poker Using Deep Learning	3, 2	0.50	Reject
1555	2.50	Psychophysical Vs. Learnt Texture Representations In Novelty Detection	3, 3, 3, 1	0.87	Reject
1556	2.33	Hierarchical Deep Reinforcement Learning Agent With Counter Self-play On Competitive Games	3, 2, 2	0.47	N/A
1557	2.33	Training Variational Auto Encoders With Discrete Latent Representations Using Importance Sampling	3, 1, 3	0.94	Reject
1558	2.33	Vectorization Methods In Recommender System	2, 2, 3	0.47	Reject
1559	2.33	Generating Text Through Adversarial Training Using Skip-thought Vectors	3, 2, 2	0.47	N/A
1560	2.33	Deli-fisher Gan: Stable And Efficient Image Generation With Structured Latent Generative Space	2, 2, 3	0.47	Reject
1561	2.33	Pixel Chem: A Representation For Predicting Material Properties With Neural Network	3, 1, 3	0.94	Reject
1562	2.33	Advanced Neuroevolution: A Gradient-free Algorithm To Train Deep Neural Networks	1, 1, 5	1.89	N/A
1563	2.25	A Synaptic Neural Network And Synapse Learning	2, 3, 2, 2	0.43	Reject
1564	2.00	Hierarchical Bayesian Modeling For Clustering Sparse Sequences In The Context Of Group Profiling	2, 2, 3, 1, 2	0.63	Reject
1565	1.50	Object Detection Deep Learning Networks For Optical Character Recognition	1, 2, 1, 2	0.50	Reject
1566	nan	Pass: Phased Attentive State Space Modeling Of Disease Progression Trajectories		nan	N/A
1567	nan	Exploring Deep Learning Using Information Theory Tools And Patch Ordering		nan	N/A
1568	nan	Teaching Machine How To Think By Natural Language: A Study On Machine Reading Comprehension		nan	N/A
1569	nan	Statistical Characterization Of Deep Neural Networks And Their Sensitivity		nan	N/A
1570	nan	Is Pgd-adversarial Training Necessary? Alternative Training Via A Soft-quantization Network With Noisy-natural Samples Only		nan	N/A
1571	nan	Isonetry : Geometry Of Critical Initializations And Training		nan	N/A
1572	nan	Scaling Up Deep Learning For Pde-based Models		nan	N/A
1573	nan	Adversarial Defense Via Data Dependent Activation Function And Total Variation Minimization		nan	N/A
1574	nan	Program Synthesis With Learned Code Idioms		nan	N/A
1575	nan	Show, Attend And Translate: Unsupervised Image Translation With Self-regularization And Attention		nan	N/A
1576	nan	Confidence-based Graph Convolutional Networks For Semi-supervised Learning		nan	N/A
1577	nan	Neural Network Bandit Learning By Last Layer Marginalization		nan	N/A
1578	nan	Neural Collobrative Networks		nan	N/A
1579	nan	Exploration In Policy Mirror Descent		nan	N/A