A Living Review of Machine Learning for Particle Physics

Modern machine learning techniques, including deep learning, is rapidly being applied, adapted, and developed for high energy physics. The goal of this document is to provide a nearly comprehensive list of citations for those developing and applying these approaches to experimental, phenomenological, or theoretical analyses. As a living document, it will be updated as often as possible to incorporate the latest developments. A list of proper (unchanging) reviews can be found within. Papers are grouped into a small set of topics to be as useful as possible. Suggestions are most welcome.

The purpose of this note is to collect references for modern machine learning as applied to particle physics. A minimal number of categories is chosen in order to be as useful as possible. Note that papers may be referenced in more than one category. The fact that a paper is listed in this document does not endorse or validate its content - that is for the community (and for peer-review) to decide. Furthermore, the classification here is a best attempt and may have flaws - please let us know if (a) we have missed a paper you think should be included, (b) a paper has been misclassified, or (c) a citation for a paper is not correct or if the journal information is now available. In order to be as useful as possible, this document will continue to evolve so please check back before you write your next paper. If you find this review helpful, please consider citing it using \cite{hepmllivingreview} in HEPML.bib.

• Reviews

  • Modern reviews

    • Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning [DOI]
    • Deep Learning and its Application to LHC Physics
    • Machine Learning in High Energy Physics Community White Paper
    • Machine learning at the energy and intensity frontiers of particle physics
    • Machine learning and the physical sciences [DOI]
    • Machine and Deep Learning Applications in Particle Physics [DOI]

  • Specialized reviews

    • The Machine Learning Landscape of Top Taggers [DOI]
    • Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
    • Graph neural networks in particle physics [DOI]
    • A Review on Machine Learning for Neutrino Experiments
    • Generative Networks for LHC events
    • Parton distribution functions
    • Simulation-based inference methods for particle physics
    • Anomaly Detection for Physics Analysis and Less than Supervised Learning
    • Graph Neural Networks for Particle Tracking and Reconstruction
    • Distributed Training and Optimization Of Neural Networks
    • The frontier of simulation-based inference
    • Machine Learning scientific competitions and datasets
    • Image-Based Jet Analysis
    • Quantum Machine Learning in High Energy Physics [DOI]
    • Sequence-based Machine Learning Models in Jet Physics

  • Classical papers

    • Neural Networks and Cellular Automata in Experimental High-energy Physics
    • Finding Gluon Jets With a Neural Trigger

• Classification

  • Parameterized classifiers

    • Parameterized neural networks for high-energy physics [DOI]

    • Approximating Likelihood Ratios with Calibrated Discriminative Classifiers

    • E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once

    • Jet images

      • How to tell quark jets from gluon jets
      • Jet-Images: Computer Vision Inspired Techniques for Jet Tagging [DOI]
      • Playing Tag with ANN: Boosted Top Identification with Pattern Recognition [DOI]
      • Jet-images — deep learning edition [DOI]
      • Quark versus Gluon Jet Tagging Using Jet Images with the ATLAS Detector
      • Boosting $H\to b\bar b$ with Machine Learning [DOI]
      • Learning to classify from impure samples with high-dimensional data [DOI]
      • Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks [DOI]
      • Deep learning in color: towards automated quark/gluon [DOI]
      • Deep-learning Top Taggers or The End of QCD? [DOI]
      • Pulling Out All the Tops with Computer Vision and Deep Learning [DOI]
      • Reconstructing boosted Higgs jets from event image segmentation
      • An Attention Based Neural Network for Jet Tagging
      • Quark-Gluon Jet Discrimination Using Convolutional Neural Networks [DOI]
      • Learning to Isolate Muons
      • Deep learning jet modifications in heavy-ion collisions

    • Event images

      • Topology classification with deep learning to improve real-time event selection at the LHC [DOI]
      • Convolutional Neural Networks with Event Images for Pileup Mitigation with the ATLAS Detector
      • Boosting $H\to b\bar b$ with Machine Learning [DOI]
      • End-to-End Physics Event Classification with the CMS Open Data: Applying Image-based Deep Learning on Detector Data to Directly Classify Collision Events at the LHC
      • Disentangling Boosted Higgs Boson Production Modes with Machine Learning
      • Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning [DOI]

    • Sequences

      • Jet Flavor Classification in High-Energy Physics with Deep Neural Networks [DOI]
      • Topology classification with deep learning to improve real-time event selection at the LHC [DOI]
      • Jet Flavour Classification Using DeepJet
      • Development of a Vertex Finding Algorithm using Recurrent Neural Network
      • Sequence-based Machine Learning Models in Jet Physics

    • Trees

      • QCD-Aware Recursive Neural Networks for Jet Physics
      • Recursive Neural Networks in Quark/Gluon Tagging

    • Graphs

      • Neural Message Passing for Jet Physics
      • Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
      • Probing stop pair production at the LHC with graph neural networks [DOI]
      • Pileup mitigation at the Large Hadron Collider with graph neural networks [DOI]
      • Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC [DOI]
      • JEDI-net: a jet identification algorithm based on interaction networks [DOI]
      • Learning representations of irregular particle-detector geometry with distance-weighted graph networks [DOI]
      • Interpretable deep learning for two-prong jet classification with jet spectra [DOI]
      • Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
      • Probing triple Higgs coupling with machine learning at the LHC
      • Casting a graph net to catch dark showers
      • Graph neural networks in particle physics [DOI]
      • Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics [DOI]
      • Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
      • Track Seeding and Labelling with Embedded-space Graph Neural Networks
      • Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
      • The Boosted Higgs Jet Reconstruction via Graph Neural Network
      • Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
      • Particle Track Reconstruction using Geometric Deep Learning
      • Jet tagging in the Lund plane with graph networks
      • Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
      • MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks

    • Sets (point clouds)

      • Energy Flow Networks: Deep Sets for Particle Jets [DOI]
      • ParticleNet: Jet Tagging via Particle Clouds [DOI]
      • ABCNet: An attention-based method for particle tagging [DOI]
      • Secondary Vertex Finding in Jets with Neural Networks
      • Equivariant Energy Flow Networks for Jet Tagging
      • Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
      • Zero-Permutation Jet-Parton Assignment using a Self-Attention Network
      • Learning to Isolate Muons
      • Point Cloud Transformers applied to Collider Physics

    • Physics-inspired basis

      • Automating the Construction of Jet Observables with Machine Learning [DOI]
      • How Much Information is in a Jet? [DOI]
      • Novel Jet Observables from Machine Learning [DOI]
      • Energy flow polynomials: A complete linear basis for jet substructure [DOI]
      • Deep-learned Top Tagging with a Lorentz Layer [DOI]
      • Resurrecting $b\bar{b}h$ with kinematic shapes

    • $W/Z$ tagging

      • Jet-images — deep learning edition [DOI]
      • Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks [DOI]
      • QCD-Aware Recursive Neural Networks for Jet Physics
      • Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques [DOI]
      • Boosted $W$ and $Z$ tagging with jet charge and deep learning [DOI]
      • Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
      • Jet tagging in the Lund plane with graph networks
      • A $W^\pm$ polarization analyzer from Deep Neural Networks

    • $H\rightarrow b\bar{b$}

      • Automating the Construction of Jet Observables with Machine Learning [DOI]
      • Boosting $H\to b\bar b$ with Machine Learning [DOI]
      • Interaction networks for the identification of boosted $H \rightarrow b\overline{b}$ decays [DOI]
      • Interpretable deep learning for two-prong jet classification with jet spectra [DOI]
      • Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques [DOI]
      • Disentangling Boosted Higgs Boson Production Modes with Machine Learning
      • Benchmarking Machine Learning Techniques with Di-Higgs Production at the LHC
      • The Boosted Higgs Jet Reconstruction via Graph Neural Network
      • Extracting Signals of Higgs Boson From Background Noise Using Deep Neural Networks

    • quarks and gluons

      • Quark versus Gluon Jet Tagging Using Jet Images with the ATLAS Detector
      • Deep learning in color: towards automated quark/gluon [DOI]
      • Recursive Neural Networks in Quark/Gluon Tagging
      • DeepJet: Generic physics object based jet multiclass classification for LHC experiments
      • Probing heavy ion collisions using quark and gluon jet substructure
      • JEDI-net: a jet identification algorithm based on interaction networks [DOI]
      • Quark-Gluon Tagging: Machine Learning vs Detector [DOI]
      • Towards Machine Learning Analytics for Jet Substructure
      • Quark Gluon Jet Discrimination with Weakly Supervised Learning [DOI]
      • Quark-Gluon Jet Discrimination Using Convolutional Neural Networks [DOI]
      • Jet tagging in the Lund plane with graph networks

    • top quark tagging

      • Playing Tag with ANN: Boosted Top Identification with Pattern Recognition [DOI]
      • DeepJet: Generic physics object based jet multiclass classification for LHC experiments
      • The Machine Learning Landscape of Top Taggers [DOI]
      • Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
      • CapsNets Continuing the Convolutional Quest [DOI]
      • Deep-learned Top Tagging with a Lorentz Layer [DOI]
      • Deep-learning Top Taggers or The End of QCD? [DOI]
      • Pulling Out All the Tops with Computer Vision and Deep Learning [DOI]
      • Boosted Top Quark Tagging and Polarization Measurement using Machine Learning
      • Morphology for Jet Classification
      • Jet tagging in the Lund plane with graph networks
      • Pulling the Higgs and Top needles from the jet stack with Feature Extended Supervised Tagging

    • strange jets

      • Strange Jet Tagging
      • A tagger for strange jets based on tracking information using long short-term memory [DOI]
      • Maximum performance of strange-jet tagging at hadron colliders

    • $b$-tagging

      • Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
      • Jet Flavor Classification in High-Energy Physics with Deep Neural Networks [DOI]
      • Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors
      • Jet Flavour Classification Using DeepJet

    • Flavor physics

      • 'Deep' Dive into $b \to c$ Anomalies: Standardized and Future-proof Model Selection Using Self-normalizing Neural Networks

    • BSM particles and models

      • Automating the Construction of Jet Observables with Machine Learning [DOI]
      • Searching for Exotic Particles in High-Energy Physics with Deep Learning [DOI]
      • Interpretable deep learning for two-prong jet classification with jet spectra [DOI]
      • A deep neural network to search for new long-lived particles decaying to jets [DOI]
      • Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter
      • Casting a graph net to catch dark showers
      • Distinguishing $W'$ Signals at Hadron Colliders Using Neural Networks
      • Deep learnig analysis of the inverse seesaw in a 3-3-1 model at the LHC
      • Comparing Traditional and Deep-Learning Techniques of Kinematic Reconstruction for polarisation Discrimination in Vector Boson Scattering
      • Invisible Higgs search through Vector Boson Fusion: A deep learning approach
      • Sensing Higgs cascade decays through memory
      • Phenomenology of vector-like leptons with Deep Learning at the Large Hadron Collider
      • WIMPs or else? Using Machine Learning to disentangle LHC signatures
      • Exploring the standard model EFT in VH production with machine learning [DOI]

    • Particle identification

      • Electromagnetic Showers Beyond Shower Shapes [DOI]
      • Survey of Machine Learning Techniques for High Energy Electromagnetic Shower Classification
      • Calorimetry with Deep Learning: Particle Classification, Energy Regression, and Simulation for High-Energy Physics
      • Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
      • Learning representations of irregular particle-detector geometry with distance-weighted graph networks [DOI]
      • Learning to Identify Electrons

    • Neutrino Detectors

      • Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber [DOI]
      • A Convolutional Neural Network Neutrino Event Classifier [DOI]
      • Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber [DOI]
      • Convolutional Neural Networks for Electron Neutrino and Electron Shower Energy Reconstruction in the NO$\nu$A Detectors
      • Event reconstruction for KM3NeT/ORCA using convolutional neural networks
      • PILArNet: Public Dataset for Particle Imaging Liquid Argon Detectors in High Energy Physics
      • Point Proposal Network for Reconstructing 3D Particle Positions with Sub-Pixel Precision in Liquid Argon Time Projection Chambers
      • Scalable, Proposal-free Instance Segmentation Network for 3D Pixel Clustering and Particle Trajectory Reconstruction in Liquid Argon Time Projection Chambers
      • Augmented Signal Processing in Liquid Argon Time Projection Chamber with Deep Neural Network
      • A Review on Machine Learning for Neutrino Experiments
      • Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
      • A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
      • Study of using machine learning for level 1 trigger decision in JUNO experiment
      • Deep-Learning-Based Kinematic Reconstruction for DUNE
      • Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE
      • Quantum Convolutional Neural Networks for High Energy Physics Data Analysis
      • Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
      • A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
      • 34th Conference on Neural Information Processing Systems

    • Direct Dark Matter Detectors

      • Boosted decision trees approach to neck alpha events discrimination in DEAP-3600 experiment
      • Improving sensitivity to low-mass dark matter in LUX using a novel electrode background mitigation technique
      • Convolutional Neural Networks for Direct Detection of Dark Matter [DOI]

    • Cosmology, Astro Particle, and Cosmic Ray physics

      • Detecting Subhalos in Strong Gravitational Lens Images with Image Segmentation
      • Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning [DOI]
      • Inverting cosmic ray propagation by Convolutional Neural Networks
      • Particle Track Reconstruction using Geometric Deep Learning
      • Deep-Learning based Reconstruction of the Shower Maximum $X_{\mathrm{max}}$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory
      • A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
      • Tackling the muon identification in water Cherenkov detectors problem for the future Southern Wide-field Gamma-ray Observatory by means of Machine Learning
      • Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using Machine Learning techniques
      • A convolutional-neural-network estimator of CMB constraints on dark matter energy injection
      • A neural network classifier for electron identification on the DAMPE experiment

    • Tracking

      • Particle Track Reconstruction with Deep Learning
      • Novel deep learning methods for track reconstruction
      • The Tracking Machine Learning challenge : Accuracy phase [DOI]
      • Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
      • An updated hybrid deep learning algorithm for identifying and locating primary vertices
      • Secondary Vertex Finding in Jets with Neural Networks
      • Track Seeding and Labelling with Embedded-space Graph Neural Networks
      • First application of machine learning algorithms to the position reconstruction in Resistive Silicon Detectors
      • Beyond 4D Tracking: Using Cluster Shapes for Track Seeding
      • Hashing and metric learning for charged particle tracking
      • Development of a Vertex Finding Algorithm using Recurrent Neural Network

    • Heavy ions

      • An equation-of-state-meter of quantum chromodynamics transition from deep learning [DOI]
      • Probing heavy ion collisions using quark and gluon jet substructure
      • Deep learning jet modifications in heavy-ion collisions
      • Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning [DOI]

    • Hyperparameters

      • Evolutionary algorithms for hyperparameter optimization in machine learning for application in high energy physics

    • Weak supervision

      • Weakly Supervised Classification in High Energy Physics [DOI]
      • Classification without labels: Learning from mixed samples in high energy physics [DOI]
      • Learning to classify from impure samples with high-dimensional data [DOI]
      • Anomaly Detection for Resonant New Physics with Machine Learning [DOI]
      • Extending the search for new resonances with machine learning [DOI]
      • Machine Learning on data with sPlot background subtraction
      • (Machine) Learning to Do More with Less
      • An operational definition of quark and gluon jets [DOI]
      • Jet Topics: Disentangling Quarks and Gluons at Colliders [DOI]
      • Dijet resonance search with weak supervision using 13 TeV pp collisions in the ATLAS detector
      • Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
      • Data-driven quark and gluon jet modification in heavy-ion collisions
      • Machine learning approach for the search of resonances with topological features at the Large Hadron Collider
      • Quark Gluon Jet Discrimination with Weakly Supervised Learning [DOI]

    • Unsupervised

      • Fuzzy Jets [DOI]
      • Metric Space of Collider Events [DOI]
      • Learning the latent structure of collider events
      • Uncovering latent jet substructure [DOI]
      • Linearized Optimal Transport for Collider Events
      • Foundations of a Fast, Data-Driven, Machine-Learned Simulator

    • Reinforcement Learning

      • Jet grooming through reinforcement learning [DOI]
      • Hierarchical clustering in particle physics through reinforcement learning
      • Real-time Artificial Intelligence for Accelerator Control: A Study at the Fermilab Booster

    • Quantum Machine Learning

      • Solving a Higgs optimization problem with quantum annealing for machine learning
      • Quantum adiabatic machine learning with zooming
      • Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
      • Event Classification with Quantum Machine Learning in High-Energy Physics
      • Quantum Convolutional Neural Networks for High Energy Physics Data Analysis
      • Application of Quantum Machine Learning using the Quantum Variational Classifier Method to High Energy Physics Analysis at the LHC on IBM Quantum Computer Simulator and Hardware with 10 qubits
      • Quantum Machine Learning in High Energy Physics [DOI]
      • Hybrid Quantum-Classical Graph Convolutional Network

    • Feature ranking

      • Mapping Machine-Learned Physics into a Human-Readable Space
      • Resurrecting $b\bar{b}h$ with kinematic shapes

    • Attention

      • Development of a Vertex Finding Algorithm using Recurrent Neural Network

    • Regularization

      • Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks

    • Software

      • On the impact of modern deep-learning techniques to the performance and time-requirements of classification models in experimental high-energy physics
      • Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree [DOI]
      • Deep topology classifiers for a more efficient trigger selection at the LHC
      • Topology classification with deep learning to improve real-time event selection at the LHC [DOI]
      • Using holistic event information in the trigger
      • Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter
      • A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications

    • Hardware/firmware

      • Fast inference of deep neural networks in FPGAs for particle physics [DOI]
      • Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML [DOI]
      • Fast inference of Boosted Decision Trees in FPGAs for particle physics [DOI]
      • GPU coprocessors as a service for deep learning inference in high energy physics
      • Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics [DOI]
      • Studying the potential of Graphcore IPUs for applications in Particle Physics
      • PDFFlow: parton distribution functions on GPU
      • FPGAs-as-a-Service Toolkit (FaaST) [DOI]
      • Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
      • PDFFlow: hardware accelerating parton density access [DOI]
      • Fast convolutional neural networks on FPGAs with hls4ml
      • Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

    • Deployment

      • MLaaS4HEP: Machine Learning as a Service for HEP

• Regression

  • Pileup

    • Pileup Mitigation with Machine Learning (PUMML) [DOI]
    • Convolutional Neural Networks with Event Images for Pileup Mitigation with the ATLAS Detector
    • Pileup mitigation at the Large Hadron Collider with graph neural networks [DOI]
    • Jet grooming through reinforcement learning [DOI]

  • Calibration

    • Parametrizing the Detector Response with Neural Networks [DOI]
    • Simultaneous Jet Energy and Mass Calibrations with Neural Networks
    • Generalized Numerical Inversion: A Neural Network Approach to Jet Calibration
    • Calorimetry with Deep Learning: Particle Classification, Energy Regression, and Simulation for High-Energy Physics
    • Per-Object Systematics using Deep-Learned Calibration
    • A deep neural network for simultaneous estimation of b jet energy and resolution
    • How to GAN Higher Jet Resolution
    • Deep learning jet modifications in heavy-ion collisions

  • Recasting

    • The BSM-AI project: SUSY-AI--generalizing LHC limits on supersymmetry with machine learning
    • Accelerating the BSM interpretation of LHC data with machine learning
    • Bayesian Neural Networks for Fast SUSY Predictions

  • Matrix elements

    • Using neural networks for efficient evaluation of high multiplicity scattering amplitudes [DOI]
    • (Machine) Learning Amplitudes for Faster Event Generation
    • $\textsf{Xsec}$: the cross-section evaluation code
    • Matrix Element Regression with Deep Neural Networks -- breaking the CPU barrier

  • Parameter estimation

    • Numerical analysis of neutrino physics within a high scale supersymmetry model via machine learning
    • Parametrized classifiers for optimal EFT sensitivity
    • MCNNTUNES: tuning Shower Monte Carlo generators with machine learning

  • Parton Distribution Functions (and related)

    • Neural-network analysis of Parton Distribution Functions from Ioffe-time pseudodistributions
    • Deep Learning Analysis of Deeply Virtual Exclusive Photoproduction
    • PDFFlow: hardware accelerating parton density access [DOI]

  • Lattice Gauge Theory

    • Equivariant flow-based sampling for lattice gauge theory
    • Lattice gauge equivariant convolutional neural networks

• Decorrelation methods.

  • Learning to Pivot with Adversarial Networks
  • Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure [DOI]
  • Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
  • uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers [DOI]
  • Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
  • Mass Agnostic Jet Taggers
  • Performance of mass-decorrelated jet substructure
  • DisCo Fever: Robust Networks Through Distance Correlation
  • QBDT, a new boosting decision tree method with systematical uncertainties into training for High Energy Physics [DOI]
  • Machine Learning Uncertainties with Adversarial Neural Networks [DOI]
  • Reducing the dependence of the neural network function to systematic uncertainties in the input space
  • New approaches for boosting to uniformity [DOI]
  • A deep neural network to search for new long-lived particles decaying to jets [DOI]
  • Adversarial domain adaptation to reduce sample bias of a high energy physics classifier
  • ABCDisCo: Automating the ABCD Method with Machine Learning
  • Enhancing searches for resonances with machine learning and moment decomposition

• Generative models / density estimation

  • GANs:

    • Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
    • Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters [DOI]
    • CaloGAN : Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks [DOI]
    • Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks [DOI]
    • How to GAN Event Subtraction
    • Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description
    • How to GAN away Detector Effects
    • 3D convolutional GAN for fast simulation
    • Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
    • Lund jet images from generative and cycle-consistent adversarial networks [DOI]
    • How to GAN LHC Events [DOI]
    • Machine Learning Templates for QCD Factorization in the Search for Physics Beyond the Standard Model [DOI]
    • DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
    • LHC analysis-specific datasets with Generative Adversarial Networks
    • Generative Models for Fast Calorimeter Simulation.LHCb case
    • Deep generative models for fast shower simulation in ATLAS
    • Regressive and generative neural networks for scalar field theory [DOI]
    • Three dimensional Generative Adversarial Networks for fast simulation
    • Generative models for fast simulation
    • Unfolding with Generative Adversarial Networks
    • Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial Networks [DOI]
    • Generating and refining particle detector simulations using the Wasserstein distance in adversarial networks [DOI]
    • Generative models for fast cluster simulations in the TPC for the ALICE experiment
    • RICH 2018 [DOI]
    • GANs for generating EFT models
    • Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network [DOI]
    • Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
    • Tips and Tricks for Training GANs with Physics Constraints
    • Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters [DOI]
    • Next Generation Generative Neural Networks for HEP
    • Calorimetry with Deep Learning: Particle Classification, Energy Regression, and Simulation for High-Energy Physics
    • Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
    • Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
    • AI-based Monte Carlo event generator for electron-proton scattering
    • DCTRGAN: Improving the Precision of Generative Models with Reweighting [DOI]
    • GANplifying Event Samples
    • Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
    • Simulating the Time Projection Chamber responses at the MPD detector using Generative Adversarial Networks
    • Explainable machine learning of the underlying physics of high-energy particle collisions
    • A Data-driven Event Generator for Hadron Colliders using Wasserstein Generative Adversarial Network [DOI]

  • Autoencoders

    • Deep Learning as a Parton Shower
    • Deep generative models for fast shower simulation in ATLAS
    • Variational Autoencoders for Anomalous Jet Tagging
    • Variational Autoencoders for Jet Simulation
    • Foundations of a Fast, Data-Driven, Machine-Learned Simulator
    • Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network

  • Normalizing flows

    • Flow-based generative models for Markov chain Monte Carlo in lattice field theory [DOI]
    • Equivariant flow-based sampling for lattice gauge theory
    • Flows for simultaneous manifold learning and density estimation
    • Exploring phase space with Neural Importance Sampling
    • Event Generation with Normalizing Flows [DOI]
    • i-flow: High-Dimensional Integration and Sampling with Normalizing Flows
    • Anomaly Detection with Density Estimation [DOI]
    • Data-driven Estimation of Background Distribution through Neural Autoregressive Flows
    • SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
    • Measuring QCD Splittings with Invertible Networks

  • Physics-inspired

    • JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
    • Binary JUNIPR: an interpretable probabilistic model for discrimination [DOI]
    • Exploring the Possibility of a Recovery of Physics Process Properties from a Neural Network Model
    • Explainable machine learning of the underlying physics of high-energy particle collisions

  • Mixture Models

    • Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning

  • Phase space generation

    • Efficient Monte Carlo Integration Using Boosted Decision
    • Exploring phase space with Neural Importance Sampling
    • Event Generation with Normalizing Flows [DOI]
    • i-flow: High-Dimensional Integration and Sampling with Normalizing Flows
    • Neural Network-Based Approach to Phase Space Integration
    • VegasFlow: accelerating Monte Carlo simulation across multiple hardware platforms
    • A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
    • Improved Neural Network Monte Carlo Simulation
    • Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
    • How to GAN Event Unweighting

  • Gaussian processes

    • Modeling Smooth Backgrounds and Generic Localized Signals with Gaussian Processes
    • Accelerating the BSM interpretation of LHC data with machine learning
    • $\textsf{Xsec}$: the cross-section evaluation code

• Anomaly detection.

  • Learning New Physics from a Machine [DOI]
  • Anomaly Detection for Resonant New Physics with Machine Learning [DOI]
  • Extending the search for new resonances with machine learning [DOI]
  • Learning Multivariate New Physics
  • Searching for New Physics with Deep Autoencoders
  • QCD or What? [DOI]
  • A robust anomaly finder based on autoencoder
  • Variational Autoencoders for New Physics Mining at the Large Hadron Collider [DOI]
  • Adversarially-trained autoencoders for robust unsupervised new physics searches [DOI]
  • Novelty Detection Meets Collider Physics
  • Guiding New Physics Searches with Unsupervised Learning [DOI]
  • Does SUSY have friends? A new approach for LHC event analysis
  • Nonparametric semisupervised classification for signal detection in high energy physics
  • Uncovering latent jet substructure [DOI]
  • Simulation Assisted Likelihood-free Anomaly Detection [DOI]
  • Anomaly Detection with Density Estimation [DOI]
  • A generic anti-QCD jet tagger
  • Transferability of Deep Learning Models in Searches for New Physics at Colliders [DOI]
  • Use of a Generalized Energy Mover's Distance in the Search for Rare Phenomena at Colliders
  • Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quark
  • Dijet resonance search with weak supervision using 13 TeV pp collisions in the ATLAS detector
  • Learning the latent structure of collider events
  • Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
  • Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
  • Variational Autoencoders for Anomalous Jet Tagging
  • Anomaly Awareness
  • Unsupervised Outlier Detection in Heavy-Ion Collisions
  • Decoding Dark Matter Substructure without Supervision
  • Mass Unspecific Supervised Tagging (MUST) for boosted jets
  • Simulation-Assisted Decorrelation for Resonant Anomaly Detection
  • Anomaly Detection With Conditional Variational Autoencoders
  • Unsupervised clustering for collider physics
  • Combining outlier analysis algorithms to identify new physics at the LHC
  • Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
  • Uncovering hidden patterns in collider events with Bayesian probabilistic models
  • Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
  • The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
  • Model-Independent Detection of New Physics Signals Using Interpretable Semi-Supervised Classifier Tests
  • Topological Obstructions to Autoencoding

• Simulation-based (`likelihood-free') Inference

  • Parameter estimation

    • Neural Networks for Full Phase-space Reweighting and Parameter Tuning [DOI]
    • Likelihood-free inference with an improved cross-entropy estimator
    • Resonance Searches with Machine Learned Likelihood Ratios
    • Constraining Effective Field Theories with Machine Learning
    • A Guide to Constraining Effective Field Theories with Machine Learning
    • MadMiner: Machine learning-based inference for particle physics [DOI]
    • Mining gold from implicit models to improve likelihood-free inference [DOI]
    • Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
    • Parameter Estimation using Neural Networks in the Presence of Detector Effects
    • Targeted Likelihood-Free Inference of Dark Matter Substructure in Strongly-Lensed Galaxies
    • Parameter Inference from Event Ensembles and the Top-Quark Mass
    • Measuring QCD Splittings with Invertible Networks
    • E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once

  • Unfolding

    • OmniFold: A Method to Simultaneously Unfold All Observables [DOI]
    • Unfolding with Generative Adversarial Networks
    • How to GAN away Detector Effects
    • Machine learning approach to inverse problem and unfolding procedure
    • Machine learning as an instrument for data unfolding
    • Advanced event reweighting using multivariate analysis
    • Unfolding by weighting Monte Carlo events
    • Binning-Free Unfolding Based on Monte Carlo Migration
    • Invertible Networks or Partons to Detector and Back Again
    • Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
    • Foundations of a Fast, Data-Driven, Machine-Learned Simulator

  • Domain adaptation

    • Reweighting with Boosted Decision Trees [DOI]
    • Neural Networks for Full Phase-space Reweighting and Parameter Tuning [DOI]
    • Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
    • DCTRGAN: Improving the Precision of Generative Models with Reweighting [DOI]

  • BSM

    • Simulation Assisted Likelihood-free Anomaly Detection [DOI]
    • Resonance Searches with Machine Learned Likelihood Ratios
    • Constraining Effective Field Theories with Machine Learning
    • A Guide to Constraining Effective Field Theories with Machine Learning
    • Mining gold from implicit models to improve likelihood-free inference [DOI]
    • MadMiner: Machine learning-based inference for particle physics [DOI]
    • Use of a Generalized Energy Mover's Distance in the Search for Rare Phenomena at Colliders

• Uncertainty Quantification

  • Interpretability

    • Jet-images — deep learning edition [DOI]
    • What is the Machine Learning? [DOI]
    • CapsNets Continuing the Convolutional Quest [DOI]
    • Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
    • Resurrecting $b\bar{b}h$ with kinematic shapes

  • Estimation

    • A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
    • AI Safety for High Energy Physics
    • Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks [DOI]

  • Mitigation

    • Adversarial learning to eliminate systematic errors: a case study in High Energy Physics
    • Machine Learning Uncertainties with Adversarial Neural Networks [DOI]
    • Learning to Pivot with Adversarial Networks
    • Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks

  • Uncertainty-aware inference

    • Constraining the Parameters of High-Dimensional Models with Active Learning [DOI]
    • Deep-Learning Jets with Uncertainties and More [DOI]
    • INFERNO: Inference-Aware Neural Optimisation [DOI]
    • Optimal statistical inference in the presence of systematic uncertainties using neural network optimization based on binned Poisson likelihoods with nuisance parameters

• Experimental results. This section is incomplete as there are many results that directly and indirectly (e.g. via flavor tagging) use modern machine learning techniques. We will try to highlight experimental results that use deep learning in a critical way for the final analysis sensitivity.

  • Final analysis discriminate for searches

    • Search for non-resonant Higgs boson pair production in the $bb\ell\nu\ell\nu$ final state with the ATLAS detector in $pp$ collisions at $\sqrt{s} [DOI]
    • Search for Higgs boson decays into a $Z$ boson and a light hadronically decaying resonance using 13 TeV $pp$ collision data from the ATLAS detector
    • Dijet resonance search with weak supervision using 13 TeV pp collisions in the ATLAS detector
    • Inclusive search for highly boosted Higgs bosons decaying to bottom quark-antiquark pairs in proton-proton collisions at $\sqrt{s} [DOI]