-
Notifications
You must be signed in to change notification settings - Fork 0
/
references.bib
1377 lines (1372 loc) · 53.7 KB
/
references.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
% Bibliography
%%%%%%%%%%%%%%%%%%%%%%%%%
% Statistical Estimation
%%%%%%%%%%%%%%%%%%%%%%%%%
%
% Parameterization
%
@article{pinheiro1996unconstrainedvariance,
title = {Unconstrained parametrizations for variance-covariance matrices},
author = {J.C. Pinheiro and D.M. Bates},
year = 1996,
journal = {Statistics and Computing},
volume = 6,
number = 3,
pages = {289--296}
}
%
% Identifiability
%
@inproceedings{roeder2020infonceidentif,
title = {On Linear Identifiability of Learned Representations},
author = {G. Roeder and L. Metz and D. Kingma},
year = 2021,
booktitle = {International Conference on Machine Learning (ICML)},
publisher = {PMLR},
volume = 139,
pages = {9030--9039}
}
@inproceedings{liu2022sslidentif,
title = {Masked Prediction: A Parameter Identifiability View},
author = {B. Liu and D. Hsu and P.K. Ravikumar and A. Risteski},
year = 2022,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
%
% Variance reduction
%
@article{glasserman1992varreduction,
title = {Some Guidelines and Guarantees for Common Random Numbers},
author = {P. Glasserman and D.D. Yao},
year = 1992,
journal = {Management Science}
}
%
% Classification
% ...(log) density-ratio estimation
%
@inproceedings{friedman2000boosting,
title = {Additive Logistic Regression : a Statistical View of Boosting},
author = {J.H. Friedman and T.J. Hastie and R. Tibshirani},
year = 2000,
journal = {The Annals of Statistics},
publisher = {Institute of Mathematical Statistics},
volume = 28,
number = 2,
pages = {337 -- 407}
}
@inproceedings{welling2002nceboosting,
title = {Self Supervised Boosting},
author = {M. Welling and R. Zemel and G.E. Hinton},
year = 2002,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {MIT Press},
volume = 15
}
@book{schapire2012boostingbook,
title = {Boosting: Foundations and Algorithms},
author = {R.E. Schapire and Y. Freund},
year = 2012,
publisher = {The MIT Press}
}
@book{sugiyama2012densityratiobook,
title = {Density Ratio Estimation in Machine Learning},
author = {M. Sugiyama and T. Suzuki and T. Kanamori},
year = 2012,
publisher = {Cambridge University Press},
place = {Cambridge}
}
@inproceedings{pellegrini2022amazondre,
title = {Don’t recommend the obvious: Estimate probability ratios},
author = {R. Pellegrini and W. Zhao and I. Murray},
year = 2022,
booktitle = {RecSys 2022}
}
%
% Scaled Bregman divergence:
% ...Importance Sampling (IS)
% ...Noise-Contrastive Estimation (NCE)
%
@book{kahn1949importancesampling,
title = {Stochastic (Monte Carlo) Attenuation Analysis},
author = {H. Kahn},
year = 1949,
publisher = {RAND Corporation},
address = {Santa Monica, CA},
doi = {}
}
@article{bennett1976ncepartition,
title = {Efficient estimation of free energy differences from Monte Carlo data},
author = {C.H. Bennett},
year = 1976,
journal = {Journal of Computational Physics},
volume = 22,
number = 2,
pages = {245--268}
}
@book{geyer1994ncepartition,
title = {Estimating Normalizing Constants and Reweighting Mixtures},
author = {C.J. Geyer},
year = 1994,
publisher = {Technical Report No. 568, School of Statistics University of Minnesota},
address = {Minneapolis, MN}
}
@article{meng1996importancesamplingext,
title = {Simulating ratios of normalizing constants via a simple identity: a theoretical exploration},
author = {X.-L. Meng and W.H. Wong},
year = 1996,
journal = {Statistica Sinica},
pages = {831--860}
}
@article{gelman1998importancesamplingext,
title = {Simulating Normalizing Constants: From Importance Sampling to Bridge Sampling to Path Sampling},
author = {A. Gelman and X.-L. Meng},
year = 1998,
journal = {Statistical Science},
volume = 13,
pages = {163--185}
}
@online{neal2008revIS,
title = {The Harmonic Mean of the Likelihood: Worst Monte Carlo Method Ever},
author = {R. Neal},
year = 2008,
url = {https://radfordneal.wordpress.com/2008/08/17/the-harmonic-mean-of-the-likelihood-worst-monte-carlo-method-ever},
urldate = {2008-08-17}
}
@inproceedings{pihlaja2010nce,
title = {A Family of Computationally Efficient and Simple Estimators for Unnormalized Statistical Models},
author = {M. Pihlaja and M. Gutmann and A. Hyv{\"a}rinen},
year = 2010,
booktitle = {Uncertainty in Artificial Intelligence (UAI)}
}
@inproceedings{gutmann2011bregman,
title = {Bregman divergence as general framework to estimate unnormalized statistical models},
author = {M. Gutmann and J. Hirayama},
year = 2011,
booktitle = {Uncertainty in Artificial Intelligence (UAI)}
}
@inproceedings{gutmann2010nce,
title = {Noise-contrastive estimation: A new estimation principle for unnormalized statistical models},
author = {M. Gutmann and A. Hyv{\"a}rinen},
year = 2010,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 9,
pages = {297--304}
}
@article{gutmann2012nce,
title = {Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics.},
author = {M. Gutmann and A. Hyv{\"a}rinen},
year = 2012,
journal = {Journal of Machine Learning Research},
volume = 13,
number = 11,
pages = {307--361}
}
@inproceedings{mnih2012condnce,
title = {A Fast and Simple Algorithm for Training Neural Probabilistic Language Models},
author = {A. Mnih and Y.W. Teh},
year = 2012,
booktitle = {International Conference on Machine Learning (ICML)},
publisher = {Omnipress},
pages = {419–426}
}
@inproceedings{liu2015ais,
title={Estimating the Partition Function by Discriminance Sampling},
author={Q. Liu and J. Peng and A.T. Ihler and J.W. Fisher III},
booktitle={Uncertainty in Artificial Intelligence (UAI)},
year={2015}
}
@article{uehara2018nce,
title = {Analysis of Noise Contrastive Estimation from the Perspective of Asymptotic Variance},
author = {M. Uehara and T. Matsuda and F. Komaki},
year = 2018,
journal = {ArXiv},
doi = {10.48550/ARXIV.1808.07983}
}
@article{rioudurand2018nce,
title = {Noise contrastive estimation: Asymptotic properties, formal comparison with {MC-MLE}},
author = {L. Riou-Durand and N. Chopin},
year = 2018,
journal = {Electronic Journal of Statistics},
publisher = {Institute of Mathematical Statistics and Bernoulli Society},
volume = 12,
number = 2,
pages = {3473 -- 3518}
}
@inproceedings{uehara2020nceefficiency,
title = {A Unified Statistically Efficient Estimation Framework for Unnormalized Models},
author = {M. Uehara and T. Kanamori and T. Takenouchi and T. Matsuda},
year = 2020,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 108,
pages = {809--819}
}
@article{matsuda2021unnormalizedmetrics,
title = {Information criteria for non-normalized models},
author = {T. Matsuda and M. Uehara and A. Hyv{\"a}rinen},
year = 2021,
journal = {Journal of Machine Learning Research},
volume = 22,
number = 158,
pages = {1--33}
}
@inproceedings{liu2021nceoptim,
title = {Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation},
author = {B. Liu and E. Rosenfeld and P. Ravikumar and A. Risteski},
year = 2022,
booktitle = {International Conference on Learning Representations (ICLR)}
}
@inproceedings{chehab2022nceoptimal,
title = {The Optimal Noise in Noise-Contrastive Learning Is Not What You Think},
author = {O. Chehab and A. Gramfort and A. Hyv{\"a}rinen},
year = 2022,
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
publisher = {PMLR},
volume = 180,
pages = {307--316}
}
@misc{chehab2022nceoptimaljmlr,
author = {O. Chehab and A. Gramfort and A. Hyv{\"a}rinen},
title = {Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation},
publisher = {arXiv},
year = {2023},
copyright = {arXiv.org perpetual, non-exclusive license}
}
@inproceedings{lee2022ncegaussiannoise,
title = {Pitfalls of Gaussians as a noise distribution in {NCE}},
author = {H. Lee and C. Pabbaraju and A. Sevekari and A. Risteski},
year = 2022,
publisher = {arXiv},
copyright = {arXiv.org perpetual, non-exclusive license}
}
@unpublished{cerou2022isoptimalnoise,
title = {{Entropy minimizing distributions are worst-case optimal importance proposals}},
author = {F. C{\'e}rou and P. H{\'e}as and M. Rousset},
year = 2022,
pdf = {https://hal.archives-ouvertes.fr/hal-03889404/file/paper_theory.pdf}
}
%
% Conditional-Noise Contrastive Estimation (CNCE)
%
@inproceedings{ceylan2018conditionalnce,
title = {Conditional Noise-Contrastive Estimation of Unnormalised Models},
author = {C. Ceylan and M.U. Gutmann},
year = 2018,
booktitle = {International Conference on Machine Learning (ICML)},
publisher = {PMLR},
volume = 80,
pages = {726--734}
}
@inproceedings{agrawal2021conditionalnce,
title = {Leveraging Time Irreversibility with Order-Contrastive Pre-training},
author = {M. Agrawal and H. Lang and M. Offin and L. Gazit and D. Sontag},
year = 2022,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 151,
pages = {2330--2353}
}
%
% Score-Matching (SM)
%
@article{hyvarinen2005scorematching,
title = {Estimation of Non-Normalized Statistical Models by Score Matching.},
author = {A. Hyv{{\"a}}rinen},
year = 2005,
journal = {Journal of Machine Learning Research},
volume = 6,
number = 24,
pages = {695--709}
}
@article{hyvarinen2006ratiomatching,
title = {Some extensions of score matching},
author = {A. Hyv{{\"a}}rinen},
year = 2007,
journal = {Computational Statistics & Data Analysis},
volume = 51,
number = 5,
pages = {2499--2512}
}
%
% Likelihood-Free Inference (LFI) or
% Approximate Bayesian Computation (ABC) or
% Simulation-Based Inference (SBI)
%
@inproceedings{durkan2020contrastivesbi,
title = {On Contrastive Learning for Likelihood-free Inference},
author = {C. Durkan and I. Murray and G. Papamakarios},
year = 2020,
booktitle = {International Conference on Machine Learning (ICML)},
publisher = {PMLR},
volume = 119,
pages = {2771--2781}
}
%
% Variational Divergence Minimization (Adversarial)
%
@inproceedings{goodfellow2014gan,
title = {Generative Adversarial Nets},
author = {I.J. Goodfellow and J. Pouget-Abadie and M. Mirza and B. Xu and D. Warde-Farley and S. Ozair and A.C. Courville and Y. Bengio},
year = 2014,
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
volume = 27
}
@inproceedings{nowozin2016fgan,
title = {{f-GAN}: Training Generative Neural Samplers using Variational Divergence Minimization},
author = {S. Nowozin and B. Cseke and R. Tomioka},
year = 2016,
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
volume = 29
}
@inproceedings{che2020ebmgan,
title = {Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling},
author = {T. Che and R. Zhang and J. Sohl-Dickstein and H. Larochelle and L. Paull and Y. Cao and Y. Bengio},
year = 2020,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {Curran Associates, Inc.},
volume = 33,
pages = {12275--12287}
}
%
% Nuisance parameters
%
@article{henmi2007isnoise,
title = {Importance Sampling Via the Estimated Sampler},
author = {M. Henmi and R. Yoshida and S. Eguchi},
year = 2007,
journal = {Biometrika},
volume = 94,
number = 4,
pages = {985--991}
}
@article{lok2021twostepestim,
title = {How estimating nuisance parameters can reduce the variance (with consistent variance estimation)},
author = {J.J. Lok},
year = 2021,
journal = {ArXiv},
volume = {abs/2109.02690}
}
%
% CNCE: adaptation
%
@article{hinton2002contrastivedivergence,
title = {Training Products of Experts by Minimizing Contrastive Divergence},
author = {G.E. Hinton},
year = 2002,
journal = {Neural Computation},
publisher = {MIT Press},
volume = 14,
number = 8,
pages = {1771--1800}
}
@article{yair2021conditionalncenoise,
title = {Contrastive Divergence Learning is a Time Reversal Adversarial Game},
author = {O. Yair and T. Michaeli},
year = 2022,
booktitle = {International Conference on Learning Representations (ICLR)}
}
%
% NCE: adaptation
%
@article{bengio2008adaptivenoise,
title = {Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model},
author = {Y. Bengio and J.-S. Senecal},
year = 2008,
journal = {IEEE Transactions on Neural Networks},
volume = 19,
number = 4,
pages = {713--722}
}
@inproceedings{hjelm2016adaptiveis,
title = {Iterative Refinement of the Approximate Posterior for Directed Belief Networks},
author = {D. Hjelm and R.R. Salakhutdinov and K. Cho and N. Jojic and V. Calhoun and J. Chung},
year = 2016,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {Curran Associates, Inc.},
volume = 29
}
@inproceedings{prangle2019adaptiveimportancesamplingflownoise,
title = {Distilling Importance Sampling for Likelihood Free Inference},
author = {D. Prangle and C. Viscardi},
year = 2019,
publisher = {arXiv},
doi = {10.48550/ARXIV.1910.03632},
url = {https://arxiv.org/abs/1910.03632},
copyright = {arXiv.org perpetual, non-exclusive license}
}
@article{gao2020fce,
title = {Flow Contrastive Estimation of Energy-Based Models},
author = {R. Gao and E. Nijkamp and D.P. Kingma and Z. Xu and A.M. Dai and Y. Nian Wu},
year = 2020,
journal = {2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {7515--7525}
}
@inproceedings{jerfel2021adaptiveimportancesamplinggmmnoise,
title = {Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence},
author = {G. Jerfel and S. Wang and C. Fannjiang and K.A. Heller and Y. Ma and M.I. Jordan},
year = 2021,
booktitle = {Uncertainty in Artificial Intelligence (UAI)}
}
@article{xing2022adaptiveIS,
title = {Improving bridge estimators via {f-GAN}},
author = {H. Xing},
year = 2022,
journal = {Statistics and Computing},
volume = 32
}
%
% NCE: annealing
%
@article{meng1996isbridgeempirical,
title = {Fitting Full-Information Item Factor Models and an Empirical Investigation of Bridge Sampling},
author = {X.-L. Meng and S. Schilling},
year = 1996,
journal = {Journal of the American Statistical Association},
publisher = {Taylor & Francis},
volume = 91,
number = 435,
pages = {1254--1267}
}
@article{torrie1977isumbrella,
title = {Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella sampling},
author = {G.M. Torrie and J.P. Valleau},
year = 1977,
journal = {Journal of Computational Physics},
volume = 23,
number = 2,
pages = {187--199}
}
@article{chen1997isratio,
title = {On Monte Carlo Methods for Estimating Ratios of Normalizing Constants},
author = {M.-H. Chen and Q.-M. Shao},
year = 1997,
journal = {The Annals of Statistics},
publisher = {Institute of Mathematical Statistics},
volume = 25,
number = 4,
pages = {1563--1594}
}
@inproceedings{rhodes2020bridgedre,
title = {Telescoping Density-Ratio Estimation},
author = {B. Rhodes and K. Xu and M.U. Gutmann},
year = 2020,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {Curran Associates, Inc.},
volume = 33,
pages = {4905--4916}
}
@inproceedings{choi2021bridgedre,
title = {Density Ratio Estimation via Infinitesimal Classification},
author = {K. Choi and C. Meng and Y. Song and S. Ermon},
year = 2022,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 151,
pages = {2552--2573}
}
%
% Independent Component Analysis (ICA)
%
@article{hyvarinen2000ica,
title = {Independent component analysis: algorithms and applications},
author = {A. Hyv{\"a}rinen and E. Oja},
year = 2000,
journal = {Neural Networks},
volume = 13,
number = 4,
pages = {411--430}
}
@inproceedings{hyvarinen2016tcl,
title = {Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear {ICA}},
author = {A. Hyv{\"a}rinen and H. Morioka},
year = 2016,
year = 2016,
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
publisher = {Curran Associates, Inc.},
volume = 29
}
@inproceedings{hyvarinen2017pcl,
title = {Nonlinear {ICA} of Temporally Dependent Stationary Sources},
author = {A. Hyv{\"a}rinen and H. Morioka},
year = 2017,
month = {20--22 Apr},
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 54,
pages = {460--469}
}
@inproceedings{hyvarinen2019gcl,
title = {Nonlinear {ICA} Using Auxiliary Variables and Generalized Contrastive Learning},
author = {A. Hyv{\"{a}}rinen and H. Sasaki and R.E. Turner},
year = 2019,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
publisher = {PMLR},
volume = 89,
pages = {859--868}
}
%
% Bregman geometry
%
@article{ovcharov2018bregmanscore,
title = {{Proper scoring rules and Bregman divergence}},
author = {E.Y. Ovcharov},
year = 2018,
journal = {Bernoulli},
publisher = {Bernoulli Society for Mathematical Statistics and Probability},
volume = 24,
number = 1,
pages = {53 -- 79}
}
@article{stummer2012scaledbregman,
title = {On Bregman Distances and Divergences of Probability Measures},
author = {W. Stummer and I. Vajda},
year = 2012,
journal = {IEEE Transactions on Information Theory},
volume = 58,
number = 3,
pages = {1277--1288}
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% Machine Learning
%%%%%%%%%%%%%%%%%%%%%%%%%
%
@article{banville2021ssleeg,
title = {Uncovering the structure of clinical EEG signals with self-supervised learning},
author = {H. Banville and O. Chehab and A. Hyv{\"a}rinen and D.-A. Engemann and A. Gramfort},
year = 2021,
journal = {Journal of Neural Engineering},
publisher = {IOP Publishing},
volume = 18,
number = 4,
pages = {046020}
}
@inproceedings{kalantidis2020hardneg,
title = {Hard Negative Mixing for Contrastive Learning},
author = {Y. Kalantidis and M.B. Sariyildiz and N. Pion and P. Weinzaepfel and D. Larlus},
year = 2020,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {Curran Associates, Inc.},
volume = 33,
pages = {21798--21809}
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% Statistical Models
%%%%%%%%%%%%%%%%%%%%%%%%%
%
% Change-of-variable models that have a tractable determinant
%
@article{papamakarios2021normalizingflows,
title = {Normalizing Flows for Probabilistic Modeling and Inference},
author = {G. Papamakarios and E. Nalisnick and D.J. Rezende and S. Mohamed and B. Lakshminarayanan},
year = 2021,
journal = {Journal of Machine Learning Research},
volume = 22,
number = 57,
pages = {1--64}
}
%
% Exponential Families
%
@article{sriperumbudur2017exponentialfamilyuniversality,
author = {B. Sriperumbudur and K. Fukumizu and A. Gretton and A. Hyv\"{a}rinen and R. Kumar},
title = {Density Estimation in Infinite Dimensional Exponential Families},
journal = {Journal of Machine Learning Research},
year = {2017},
volume = {18},
number = {57},
pages = {1--59},
}
@misc{nielsen2011exponentialfamilyreview,
title={Statistical exponential families: A digest with flash cards},
author={F. Nielsen and V. Garcia},
year={2011},
eprint={0911.4863},
archivePrefix={arXiv},
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% Model Architectures
%%%%%%%%%%%%%%%%%%%%%%%%%
%
@article{dinh2016realnvp,
title = {Density estimation using {Real NVP}},
author = {L. Dinh and J.N. Sohl-Dickstein and S. Bengio},
year = 2016,
journal = {ArXiv},
volume = {abs/1605.08803}
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% Code
%%%%%%%%%%%%%%%%%%%%%%%%%
%
@incollection{pytorch,
title = {PyTorch: An Imperative Style, High-Performance Deep Learning Library},
author = {A. Paszke and S. Gross and F. Massa and A. Lerer and J. Bradbury and G. Chanan and T. Killeen and Z. Lin and N. Gimelshein and L. Antiga and A. Desmaison and A. Kopf and E. Yang and Z. DeVito and M. Raison and A. Tejani and S. Chilamkurthy and B. Steiner and L. Fang and J. Bai and S. Chintala},
year = 2019,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
publisher = {Curran Associates, Inc.},
pages = {8024--8035}
}
@article{scipy,
title = {{{SciPy} 1.0: Fundamental Algorithms for Scientific Computing in Python}},
author = {P. Virtanen and R. Gommers and T.E. Oliphant and M. Haberland and T. Reddy and D. Cournapeau and E. Burovski and P. Peterson and W. Weckesser and J. Bright and S.J. {van der Walt} and M. Brett and J. Wilson and J.K. Millman and N. Mayorov and A.R.J. Nelson and E. Jones and R. Kern and E. Larson and C.J. Carey and I. Polat and Y. Feng and E.W. Moore and J. {VanderPlas} and D. Laxalde and J. Perktold and R. Cimrman and I. Henriksen and E.A. Quintero and C.R. Harris and A.M. Archibald and A.H. Ribeiro and F. Pedregosa and P. {van Mulbregt} and {SciPy 1.0 Contributors}},
year = 2020,
journal = {Nature Methods},
volume = 17,
pages = {261--272}
}
@article{matplotlib,
title = {Matplotlib: A 2D graphics environment},
author = {J.D. Hunter},
year = 2007,
journal = {Computing in science \& engineering},
publisher = {IEEE Computer Society},
volume = 9,
number = 3,
pages = {90--95}
}
@article{numpy,
title = {Array programming with {NumPy}},
author = {C.R. Harris and K.J. Millman and S.J. van der Walt and R. Gommers and P. Virtanen and D. Cournapeau and E. Wieser and J. Taylor and S. Berg and N.J. Smith and R. Kern and M. Picus and S. Hoyer and M.H. van Kerkwijk and M. Brett and A. Haldane and J. Fern{\'a}ndez del R{\'i}o and M. Wiebe and P. Peterson and P. G{\'e}rard-Marchant and K. Sheppard and T. Reddy and W. Weckesser and H. Abbasi and C. Gohlke and T.E. Oliphant},
year = 2020,
journal = {Nature},
publisher = {Springer Science and Business Media {LLC}},
volume = 585,
number = 7825,
pages = {357--362}
}
@article{scikit-learn,
title = {{Scikit-learn: Machine Learning in Python }},
author = {Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V. and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
year = 2011,
journal = {Journal of Machine Learning Research},
volume = 12,
pages = {2825--2830}
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% Sampling
%%%%%%%%%%%%%%%%%%%%%%%%%
%
% Optimal proposal
%
@article{gelman1997bestproposalvarrwm,
title = {{Weak convergence and optimal scaling of random walk Metropolis algorithms}},
author = {A. Gelman and W. R. Gilks and G. O. Roberts},
year = 1997,
journal = {The Annals of Applied Probability},
publisher = {Institute of Mathematical Statistics},
volume = 7,
number = 1,
pages = {110 -- 120}
}
@article{roberts1998bestproposalvarmala,
title = {Optimal scaling of discrete approximations to Langevin diffusions},
author = {G.O. Roberts and J.S. Rosenthal},
year = 1998,
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
volume = 60
}
%%%%%%%%%%%%%%%%%%%%%%%%%
% Reference Books
%%%%%%%%%%%%%%%%%%%%%%%%%
%
@inbook{vandervaart2002semiparam,
title = {Semiparametric statistics},
author = {A.W. {van der Vaart}},
year = 2002,
booktitle = {Lectures on probability theory and statistics (Saint-Flour, 1999)},
publisher = {Springer},
series = {Lecture Notes in Math.}
}
@book{vandervaart2000asympstats,
title = {Asymptotic Statistics},
author = {A.W. {van der Vaart}},
year = 2000,
publisher = {Cambridge University Press},
series = {Asymptotic Statistics}
}
@proceedings{bousquet2004stattheory,
title = {Advanced Lectures on Machine Learning, ML Summer Schools 2003, Canberra, Australia, February 2-14, 2003, T{\"u}bingen, Germany, August 4-16, 2003, Revised Lectures},
year = 2004,
booktitle = {Advanced Lectures on Machine Learning},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
volume = 3176,
editor = {O. Bousquet and U. von Luxburg and G. R{\"a}tsch}
}
@book{boyd2004optimbook,
title = {Convex Optimization},
author = {S. Boyd and L. Vandenberghe},
year = 2004,
publisher = {Cambridge University Press}
}
%
%%%%%%%%%%%%%%%%%%%%%%%%%
% To clean up
%%%%%%%%%%%%%%%%%%%%%%%%%
%
@inproceedings{huszar2015gan,
title = {How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?},
author = {F. Huszár},
year = 2015,
eprint = {1511.05101},
archiveprefix = {arXiv},
primaryclass = {stat.ML}
}
@inproceedings{kingma2014vae,
title = {{Auto-Encoding Variational Bayes}},
author = {D.P. Kingma and M. Welling},
year = 2014,
booktitle = {2nd International Conference on Learning Representations (ICLR), {International Conference on Learning Representations (ICLR)} 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings},
eprintclass = {stat.ML},
eprinttype = {arXiv}
}
@inproceedings{rommel2021dataaugment,
title = {CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals},
author = {C. Rommel and T. Moreau and A. Gramfort},
year = 2021,
eprint = {2106.13695},
archiveprefix = {arXiv},
primaryclass = {cs.LG}
}
@article{dieng2019gan,
title = {Prescribed Generative Adversarial Networks},
author = {A.B. Dieng and F.J.R. Ruiz and D.M. Blei and M.K. Titsias},
year = 2019,
journal = {ArXiv},
volume = {abs/1910.04302}
}
@article{mohamed2016implicitgen,
title = {Learning in Implicit Generative Models},
author = {S. Mohamed and B. Lakshminarayanan},
year = 2016,
journal = {ArXiv},
volume = {abs/1610.03483}
}
@inproceedings{mikolov2013nce,
title = {Distributed Representations of Words and Phrases and their Compositionality},
author = {T. Mikolov and I. Sutskever and K. Chen and G.S. Corrado and J. Dean},
year = 2013,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@inproceedings{mnih2012nce,
title = {A fast and simple algorithm for training neural probabilistic language models},
author = {A. Mnih and Y.W. Teh},
year = 2012,
booktitle = {International Conference on Machine Learning (ICML)}
}
@article{defazio2014saga,
title = {SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives},
author = {A. Defazio and F.R. Bach and S. Lacoste-Julien},
year = 2014,
journal = {ArXiv},
volume = {abs/1407.0202}
}
@conference{gresele2020jacobiandeep,
title = {Relative gradient optimization of the Jacobian term in unsupervised deep learning},
author = {Gresele, L. and Fissore, G. and Javaloy, A. and Sch{\"o}lkopf, B. and Hyv{\"a}rinen, A.},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@inproceedings{das2021chisquare,
title = {A method to integrate and classify normal distributions},
author = {Abhranil Das and Wilson S Geisler},
year = 2021,
eprint = {2012.14331},
archiveprefix = {arXiv},
primaryclass = {stat.ML}
}
@inproceedings{chen2020simclr,
title = {A Simple Framework for Contrastive Learning of Visual Representations},
author = {T. Chen and S. Kornblith and M. Norouzi and G. Hinton},
year = 2020,
booktitle = {International Conference on Machine Learning (ICML)}
}
@article{vanoord2018cpc,
title = {Representation Learning with Contrastive Predictive Coding},
author = {A. van den Oord and Y. Li and O. Vinyals},
year = 2018,
journal = {CoRR},
eprinttype = {arXiv},
eprint = {1807.03748}
}
@inproceedings{gresele2020jacobian,
title = {Relative gradient optimization of the Jacobian term in unsupervised deep learning},
author = {L. Gresele and G. Fissore and A. Javaloy and B. Sch\"{o}lkopf and A. Hyv{\"a}rinen},
year = 2020,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@article{parascandolo2021invariance,
title = {Learning explanations that are hard to vary},
author = {Giambattista Parascandolo and Alexander Neitz and Antonio Orvieto and Luigi Gresele and Bernhard Sch{\"o}lkopf},
year = 2021,
journal = {ArXiv},
volume = {abs/2009.00329}
}
@article{banville2020ssleeg,
title = {Uncovering the structure of clinical EEG signals with self-supervised learning},
author = {H.J. Banville and O. Chehab and A. Hyv{\"a}rinen and D.A. Engemann and A. Gramfort},
year = 2020,
journal = {Journal of Neural Engineering}
}
@inproceedings{halva2020hmmica,
title = {Hidden Markov Nonlinear {ICA}: Unsupervised Learning from Nonstationary Time Series},
author = {Hermanni Halva and Aapo Hyv{\"a}rinen},
year = 2020
}
@inproceedings{ma2018contrastive,
title = {Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency},
author = {Zhuang Ma and Michael Collins},
year = 2018,
booktitle = {EMNLP}
}
@article{chen2021cdre,
title = {Continual Density Ratio Estimation in an Online Setting},
author = {Yu Chen and Song Liu and Tom Diethe and Peter A. Flach},
year = 2021,
journal = {ArXiv},
volume = {abs/2103.05276}
}
@article{bortoli2021diffusionot,
title = {Diffusion Schr{\"o}dinger Bridge with Applications to Score-Based Generative Modeling},
author = {Valentin De Bortoli and James Thornton and Jeremy Heng and A. Doucet},
year = 2021,
journal = {ArXiv},
volume = {abs/2106.01357}
}
@article{song2021diffusionsde,
title = {Score-Based Generative Modeling through Stochastic Differential Equations},
author = {Yang Song and Jascha Sohl-Dickstein and Diederik P. Kingma and Abhishek Kumar and Stefano Ermon and Ben Poole},
year = 2021,
journal = {ArXiv},
volume = {abs/2011.13456}
}
@inproceedings{poole2019infoestimators,
title = {On Variational Bounds of Mutual Information},
author = {Ben Poole and Sherjil Ozair and A{\"a}ron van den Oord and Alexander A. Alemi and G. Tucker},
year = 2019,
booktitle = {International Conference on Machine Learning (ICML)}
}
@article{jozefowicz2016singleranking,
title = {Exploring the Limits of Language Modeling},
author = {Rafal J{\'o}zefowicz and Oriol Vinyals and Mike Schuster and Noam M. Shazeer and Yonghui Wu},
year = 2016,
journal = {ArXiv},
volume = {abs/1602.02410}
}
@article{qin1998densityratio,
title = {Inferences for Case-Control and Semiparametric Two-Sample Density Ratio Models},
author = {Jing Qin},
year = 1998,
journal = {Biometrika},
publisher = {[Oxford University Press, Biometrika Trust]}
}
@inproceedings{zimmermann2021infonceidentif,
title = {Contrastive Learning Inverts the Data Generating Process},
author = {Zimmermann, Roland S. and Sharma, Yash and Schneider, Steffen and Bethge, Matthias and Brendel, Wieland},
year = 2021,
booktitle = {International Conference on Machine Learning (ICML)}
}
@inproceedings{wang2020sslgeometry,
title = {Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere},
author = {Tongzhou Wang and Phillip Isola},
year = 2020,
booktitle = {International Conference on Machine Learning (ICML)}
}
@inproceedings{liu2021condncetimeseries,
title = {Contrastive learning of strong-mixing continuous-time stochastic processes},
author = {Bingbin Liu and Pradeep Ravikumar and Andrej Risteski},
year = 2021,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)}
}
@inproceedings{srivastava2020ratiomatch,
title = {Generative Ratio Matching Networks},
author = {Akash Srivastava and Kai Xu and Michael U. Gutmann and Charles Sutton},
year = 2020,
booktitle = {International Conference on Learning Representations (ICLR)}
}
@article{chuang2020debiasedinfonce,
title = {Debiased Contrastive Learning},
author = {Ching-Yao Chuang and Joshua Robinson and Yen-Chen Lin and Antonio Torralba and Stefanie Jegelka},
year = 2020,
journal = {ArXiv},
volume = {abs/2007.00224}
}
@article{nguyen2010ratioestim,
title = {Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization},
author = {X. Nguyen and M.J. Wainwright and M.I. Jordan},
year = 2010,
journal = {IEEE Transactions on Information Theory}
}
@inproceedings{chen2020dre,
title = {Continual Density Ratio Estimation ({\{}CDRE{\}}): A new method for evaluating generative models in continual learning},
author = {Yu Chen and Song Liu and Tom Diethe and Peter Flach},
year = 2020,
url = {https://openreview.net/forum?id=HJemQJBKDr}
}
@inproceedings{liu2021contrastivesde,
title = {Contrastive learning of strong-mixing continuous-time stochastic processes},
author = {Bingbin Liu and Pradeep Ravikumar and Andrej Risteski},
year = 2021,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)}
}
@book{owenmontecarlobook,
title = {Monte Carlo theory, methods and examples},
author = {A.B. Owen},
year = 2013,
}
@inproceedings{labeau2018ranking,
title = {Learning with Noise-Contrastive Estimation: Easing training by learning to scale},
author = {Matthieu Labeau and A. Allauzen},
year = 2018,
booktitle = {COLING}
}
@inproceedings{bengio2003adaptivesamples,
title = {Quick Training of Probabilistic Neural Nets by Importance Sampling},
author = {Yoshua Bengio and Jean-S{\'e}bastien Senecal},
year = 2003,
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)}
}
@article{finn2016ebm,
title = {A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models},
author = {Chelsea Finn and Paul Francis Christiano and Pieter Abbeel and Sergey Levine},
year = 2016,
journal = {ArXiv},
volume = {abs/1611.03852}
}
@article{gower2019sgdcvrate,
title = {SGD: General Analysis and Improved Rates},
author = {Robert Mansel Gower and Nicolas Loizou and Xun Qian and Alibek Sailanbayev and Egor Shulgin and Peter Richt{\'a}rik},
year = 2019,
journal = {ArXiv},
volume = {abs/1901.09401}
}
@inproceedings{kingma2018glow,
title = {Glow: Generative Flow with Invertible 1x1 Convolutions},
author = {Kingma, Durk P and Dhariwal, Prafulla},
year = 2018,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@inproceedings{nowozin2015ess,
title = {Effective Sample Size blogpost},
author = {S. Nowozin},
year = 2015,
howpublished = {\url{http://www.nowozin.net/sebastian/blog/effective-sample-size-in-importance-sampling.html}}
}
@inproceedings{chatterjee2015samplesize,
title = {The sample size required in importance sampling},
author = {S. Chatterjee and P. Diaconis},
year = 2015,
publisher = {arXiv},
doi = {10.48550/ARXIV.1511.01437},
copyright = {arXiv.org perpetual, non-exclusive license}
}
@inproceedings{johnson2013svrg,
title = {Accelerating Stochastic Gradient Descent using Predictive Variance Reduction},
author = {Johnson, Rie and Zhang, Tong},
year = 2013,
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@article{evans1995ess,
title = {{Methods for Approximating Integrals in Statistics with Special Emphasis on Bayesian Integration Problems}},
author = {Michael Evans and Tim Swartz},
year = 1995,
journal = {Statistical Science},
publisher = {Institute of Mathematical Statistics}
}
@article{papamakarios2021flows,
title = {Normalizing Flows for Probabilistic Modeling and Inference},
author = {George Papamakarios and Eric T. Nalisnick and Danilo Jimenez Rezende and Shakir Mohamed and Balaji Lakshminarayanan},
year = 2021,
journal = {Journal of Machine Learning Research}
}
@article{sejourne2019sinkhorn,
title = {Sinkhorn Divergences for Unbalanced Optimal Transport},
author = {Thibault S'ejourn'e and Jean Feydy and Franccois-Xavier Vialard and Alain Trouv'e and Gabriel Peyr'e},
year = 2019,
journal = {ArXiv},
volume = {abs/1910.12958}
}
@article{minka2001ep,
title = {Expectation Propagation for approximate Bayesian inference},
author = {Thomas P. Minka},
year = 2001,
journal = {ArXiv},