-
Notifications
You must be signed in to change notification settings - Fork 0
/
Bibliography.bib
2920 lines (2550 loc) · 96.3 KB
/
Bibliography.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
@misc{lecun1994mnist,
title={The {MNIST} database of handwritten digits},
author={Yann LeCun and Corinna Cortes and Christopher J.~C. Burges},
howpublished={\url{http://yann.lecun.com/exdb/mnist/}, 1994},
year={1996}
}
@inproceedings{sabatelli2021transferability,
title={On The Transferability of Deep-Q Networks},
author={Sabatelli, Matthia and Geurts, Pierre},
booktitle={Deep Reinforcement Learning Workshop of the 35th Conference on Neural Information Processing Systems},
year={2021}
}
@misc{dogoimage,
howpublished = "\url{https://www.aspexit.com/neural-network-lets-try-to-demystify-all-this-a-little-bit-3-application-to-images/}"
}
@inproceedings{dai2008self,
title={Self-taught clustering},
author={Dai, Wenyuan and Yang, Qiang and Xue, Gui-Rong and Yu, Yong},
booktitle={Proceedings of the 25th international conference on Machine learning},
pages={200--207},
year={2008}
}
@article{zhao2011reinforcement,
title={Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer},
author={Zhao, Yufan and Zeng, Donglin and Socinski, Mark A and Kosorok, Michael R},
journal={Biometrics},
volume={67},
number={4},
pages={1422--1433},
year={2011},
publisher={Wiley Online Library}
}
@article{zhu2016robust,
title={Robust joint graph sparse coding for unsupervised spectral feature selection},
author={Zhu, Xiaofeng and Li, Xuelong and Zhang, Shichao and Ju, Chunhua and Wu, Xindong},
journal={IEEE transactions on neural networks and learning systems},
volume={28},
number={6},
pages={1263--1275},
year={2016},
publisher={IEEE}
}
@article{liu2021efficient,
title={Efficient Training of Visual Transformers with Small Datasets},
author={Liu, Yahui and Sangineto, Enver and Bi, Wei and Sebe, Nicu and Lepri, Bruno and Nadai, Marco},
journal={Advances in Neural Information Processing Systems},
volume={34},
year={2021}
}
@article{silver2017mastering,
title={Mastering the game of go without human knowledge},
author={Silver, David and Schrittwieser, Julian and Simonyan, Karen and Antonoglou, Ioannis and Huang, Aja and Guez, Arthur and Hubert, Thomas and Baker, Lucas and Lai, Matthew and Bolton, Adrian and others},
journal={nature},
volume={550},
number={7676},
pages={354--359},
year={2017},
publisher={Nature Publishing Group}
}
@article{yosinski2014transferable,
title={How transferable are features in deep neural networks?},
author={Yosinski, Jason and Clune, Jeff and Bengio, Yoshua and Lipson, Hod},
journal={arXiv preprint arXiv:1411.1792},
year={2014}
}
@article{zhu2020transfer,
title={Transfer Learning in Deep Reinforcement Learning: A Survey},
author={Zhu, Zhuangdi and Lin, Kaixiang and Zhou, Jiayu},
journal={arXiv preprint arXiv:2009.07888},
year={2020}
}
@inproceedings{tirinzoni2018transfer,
title={Transfer of value functions via variational methods},
author={Tirinzoni, Andrea and Sanchez, Rafael Rodriguez and Restelli, Marcello},
booktitle={Advances in Neural Information Processing Systems},
pages={6179--6189},
year={2018}
}
@article{ha2018world,
title={World models},
author={Ha, David and Schmidhuber, J{\"u}rgen},
journal={arXiv preprint arXiv:1803.10122},
year={2018}
}
@inproceedings{zhu2017target,
title={Target-driven visual navigation in indoor scenes using deep reinforcement learning},
author={Zhu, Yuke and Mottaghi, Roozbeh and Kolve, Eric and Lim, Joseph J and Gupta, Abhinav and Fei-Fei, Li and Farhadi, Ali},
booktitle={2017 IEEE international conference on robotics and automation (ICRA)},
pages={3357--3364},
year={2017},
organization={IEEE}
}
@article{chen2021improving,
title={Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings},
author={Chen, Lili and Lee, Kimin and Srinivas, Aravind and Abbeel, Pieter},
journal={arXiv preprint arXiv:2103.02886},
year={2021}
}
@article{landolfi2019model,
title={A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning},
author={Landolfi, Nicholas C and Thomas, Garrett and Ma, Tengyu},
journal={arXiv preprint arXiv:1907.04964},
year={2019}
}
@article{rusu2016progressive,
title={Progressive neural networks},
author={Rusu, Andrei A and Rabinowitz, Neil C and Desjardins, Guillaume and Soyer, Hubert and Kirkpatrick, James and Kavukcuoglu, Koray and Pascanu, Razvan and Hadsell, Raia},
journal={arXiv preprint arXiv:1606.04671},
year={2016}
}
@article{vandaele2021deep,
title={Deep learning for automated river-level monitoring through river-camera images: an approach based on water segmentation and transfer learning},
author={Vandaele, Remy and Dance, Sarah L and Ojha, Varun},
journal={Hydrology and Earth System Sciences},
volume={25},
number={8},
pages={4435--4453},
year={2021},
publisher={Copernicus GmbH}
}
@inproceedings{hafner2019learning,
title={Learning latent dynamics for planning from pixels},
author={Hafner, Danijar and Lillicrap, Timothy and Fischer, Ian and Villegas, Ruben and Ha, David and Lee, Honglak and Davidson, James},
booktitle={International Conference on Machine Learning},
pages={2555--2565},
year={2019},
organization={PMLR}
}
@article{hafner2019dream,
title={Dream to control: Learning behaviors by latent imagination},
author={Hafner, Danijar and Lillicrap, Timothy and Ba, Jimmy and Norouzi, Mohammad},
journal={arXiv preprint arXiv:1912.01603},
year={2019}
}
@article{hafner2020mastering,
title={Mastering atari with discrete world models},
author={Hafner, Danijar and Lillicrap, Timothy and Norouzi, Mohammad and Ba, Jimmy},
journal={arXiv preprint arXiv:2010.02193},
year={2020}
}
@inproceedings{kim2019deepmellow,
title={Deepmellow: removing the need for a target network in deep Q-learning},
author={Kim, Seungchan and Asadi, Kavosh and Littman, Michael and Konidaris, George},
booktitle={Proceedings of the Twenty Eighth International Joint Conference on Artificial Intelligence},
year={2019}
}
@article{piche2021beyond,
title={Beyond Target Networks: Improving Deep $ Q $-learning with Functional Regularization},
author={Pich{\'e}, Alexandre and Marino, Joseph and Marconi, Gian Maria and Pal, Christopher and Khan, Mohammad Emtiyaz},
journal={arXiv preprint arXiv:2106.02613},
year={2021}
}
@inproceedings{jin2011transferring,
title={Transferring topical knowledge from auxiliary long texts for short text clustering},
author={Jin, Ou and Liu, Nathan N and Zhao, Kai and Yu, Yong and Yang, Qiang},
booktitle={Proceedings of the 20th ACM international conference on Information and knowledge management},
pages={775--784},
year={2011}
}
@inproceedings{wang2008transferred,
title={Transferred dimensionality reduction},
author={Wang, Zheng and Song, Yangqiu and Zhang, Changshui},
booktitle={Joint European conference on machine learning and knowledge discovery in databases},
pages={550--565},
year={2008},
organization={Springer}
}
@article{qian2015cluster,
title={Cluster prototypes and fuzzy memberships jointly leveraged cross-domain maximum entropy clustering},
author={Qian, Pengjiang and Jiang, Yizhang and Deng, Zhaohong and Hu, Lingzhi and Sun, Shouwei and Wang, Shitong and Muzic, Raymond F},
journal={IEEE transactions on cybernetics},
volume={46},
number={1},
pages={181--193},
year={2015},
publisher={IEEE}
}
@article{zhu2013self,
title={Self-taught dimensionality reduction on the high-dimensional small-sized data},
author={Zhu, Xiaofeng and Huang, Zi and Yang, Yang and Shen, Heng Tao and Xu, Changsheng and Luo, Jiebo},
journal={Pattern Recognition},
volume={46},
number={1},
pages={215--229},
year={2013},
publisher={Elsevier}
}
@misc{raghakotkerasvis,
title={keras-vis},
author={Kotikalapudi, Raghavendra and contributors},
year={2017},
publisher={GitHub},
howpublished={\url{https://github.com/raghakot/keras-vis}},
}
@article{xiao2017fashion,
title={Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms},
author={Xiao, Han and Rasul, Kashif and Vollgraf, Roland},
journal={arXiv preprint arXiv:1708.07747},
year={2017}
}
@article{clanuwat2018deep,
title={Deep learning for classical japanese literature},
author={Clanuwat, Tarin and Bober-Irizar, Mikel and Kitamoto, Asanobu and Lamb, Alex and Yamamoto, Kazuaki and Ha, David},
journal={arXiv preprint arXiv:1812.01718},
year={2018}
}
@inproceedings{langley2006transfer,
title={Transfer of knowledge in cognitive systems},
author={Langley, Pat},
booktitle={Talk, workshop on Structural Knowledge Transfer for Machine Learning at the Twenty-Third International Conference on Machine Learning},
year={2006}
}
@inproceedings{arnold2007comparative,
title={A comparative study of methods for transductive transfer learning},
author={Arnold, Andrew and Nallapati, Ramesh and Cohen, William W},
booktitle={Seventh IEEE international conference on data mining workshops (ICDMW 2007)},
pages={77--82},
year={2007},
organization={IEEE}
}
@article{pan2009survey,
title={A survey on transfer learning},
author={Pan, Sinno Jialin and Yang, Qiang},
journal={IEEE Transactions on knowledge and data engineering},
volume={22},
number={10},
pages={1345--1359},
year={2009},
publisher={IEEE}
}
@article{zhuang2020comprehensive,
title={A comprehensive survey on transfer learning},
author={Zhuang, Fuzhen and Qi, Zhiyuan and Duan, Keyu and Xi, Dongbo and Zhu, Yongchun and Zhu, Hengshu and Xiong, Hui and He, Qing},
journal={Proceedings of the IEEE},
volume={109},
number={1},
pages={43--76},
year={2020},
publisher={IEEE}
}
@inproceedings{taylor2008transferring,
title={Transferring instances for model-based reinforcement learning},
author={Taylor, Matthew E and Jong, Nicholas K and Stone, Peter},
booktitle={Joint European conference on machine learning and knowledge discovery in databases},
pages={488--505},
year={2008},
organization={Springer}
}
@inproceedings{lazaric2008transfer,
title={Transfer of samples in batch reinforcement learning},
author={Lazaric, Alessandro and Restelli, Marcello and Bonarini, Andrea},
booktitle={Proceedings of the 25th international conference on Machine learning},
pages={544--551},
year={2008}
}
@article{taylor2009transfer,
title={Transfer learning for reinforcement learning domains: A survey.},
author={Taylor, Matthew E and Stone, Peter},
journal={Journal of Machine Learning Research},
volume={10},
number={7},
year={2009}
}
@inproceedings{sharif2014cnn,
title={CNN features off-the-shelf: an astounding baseline for recognition},
author={Sharif Razavian, Ali and Azizpour, Hossein and Sullivan, Josephine and Carlsson, Stefan},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition workshops},
pages={806--813},
year={2014}
}
@article{wang2014action,
title={Action recognition and detection by combining motion and appearance features},
author={Wang, Limin and Qiao, Yu and Tang, Xiaoou},
journal={THUMOS14 Action Recognition Challenge},
volume={1},
number={2},
pages={2},
year={2014},
publisher={Citeseer}
}
@article{zhou2014learning,
title={Learning deep features for scene recognition using places database},
author={Zhou, Bolei and Lapedriza, Agata and Xiao, Jianxiong and Torralba, Antonio and Oliva, Aude},
year={2014},
publisher={Neural Information Processing Systems Foundation}
}
@inproceedings{van2015off,
title={Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans},
author={Van Ginneken, Bram and Setio, Arnaud AA and Jacobs, Colin and Ciompi, Francesco},
booktitle={2015 IEEE 12th International symposium on biomedical imaging (ISBI)},
pages={286--289},
year={2015},
organization={IEEE}
}
@inproceedings{sharma2015adapting,
title={Adapting off-the-shelf CNNs for word spotting \& recognition},
author={Sharma, Arjun and others},
booktitle={2015 13th International Conference on Document Analysis and Recognition (ICDAR)},
pages={986--990},
year={2015},
organization={IEEE}
}
@article{nguyen2017iris,
title={Iris recognition with off-the-shelf CNN features: A deep learning perspective},
author={Nguyen, Kien and Fookes, Clinton and Ross, Arun and Sridharan, Sridha},
journal={IEEE Access},
volume={6},
pages={18848--18855},
year={2017},
publisher={IEEE}
}
@inproceedings{laroche2017transfer,
title={Transfer reinforcement learning with shared dynamics},
author={Laroche, Romain and Barlier, Merwan},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={31},
number={1},
year={2017}
}
@article{lowe2004distinctive,
title={Distinctive image features from scale-invariant keypoints},
author={Lowe, David G},
journal={International journal of computer vision},
volume={60},
number={2},
pages={91--110},
year={2004},
publisher={Springer}
}
@inproceedings{dalal2005histograms,
title={Histograms of oriented gradients for human detection},
author={Dalal, Navneet and Triggs, Bill},
booktitle={2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05)},
volume={1},
pages={886--893},
year={2005},
organization={Ieee}
}
@inproceedings{kornblith2019better,
title={Do better imagenet models transfer better?},
author={Kornblith, Simon and Shlens, Jonathon and Le, Quoc V},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={2661--2671},
year={2019}
}
@article{mikolov2013efficient,
title={Efficient estimation of word representations in vector space},
author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
journal={arXiv preprint arXiv:1301.3781},
year={2013}
}
@article{brown2020language,
title={Language models are few-shot learners},
author={Brown, Tom B and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
journal={arXiv preprint arXiv:2005.14165},
year={2020}
}
@article{devlin2018bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1810.04805},
year={2018}
}
@article{rosset2020knowledge,
title={Knowledge-Aware Language Model Pretraining},
author={Rosset, Corby and Xiong, Chenyan and Phan, Minh and Song, Xia and Bennett, Paul and Tiwary, Saurabh},
journal={arXiv preprint arXiv:2007.00655},
year={2020}
}
@article{huh2016makes,
title={What makes ImageNet good for transfer learning?},
author={Huh, Minyoung and Agrawal, Pulkit and Efros, Alexei A},
journal={arXiv preprint arXiv:1608.08614},
year={2016}
}
@article{farebrother2018generalization,
title={Generalization and regularization in DQN},
author={Farebrother, Jesse and Machado, Marlos C and Bowling, Michael},
journal={arXiv preprint arXiv:1810.00123},
year={2018}
}
@article{parisotto2015actor,
title={Actor-mimic: Deep multitask and transfer reinforcement learning},
author={Parisotto, Emilio and Ba, Jimmy Lei and Salakhutdinov, Ruslan},
journal={arXiv preprint arXiv:1511.06342},
year={2015}
}
@article{tyo2020transferable,
title={How transferable are the representations learned by deep q agents?},
author={Tyo, Jacob and Lipton, Zachary},
journal={arXiv preprint arXiv:2002.10021},
year={2020}
}
@article{mensink2021factors,
title={Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types},
author={Mensink, Thomas and Uijlings, Jasper and Kuznetsova, Alina and Gygli, Michael and Ferrari, Vittorio},
journal={arXiv preprint arXiv:2103.13318},
year={2021}
}
@inproceedings{tirinzoni2018importance,
title={Importance weighted transfer of samples in reinforcement learning},
author={Tirinzoni, Andrea and Sessa, Andrea and Pirotta, Matteo and Restelli, Marcello},
booktitle={International Conference on Machine Learning},
pages={4936--4945},
year={2018},
organization={PMLR}
}
@article{sasso2021fractional,
title={Fractional Transfer Learning for Deep Model-Based Reinforcement Learning},
author={Sasso, Remo and Sabatelli, Matthia and Wiering, Marco A},
journal={arXiv preprint arXiv:2108.06526},
year={2021}
}
@incollection{lazaric2012transfer,
title={Transfer in reinforcement learning: a framework and a survey},
author={Lazaric, Alessandro},
booktitle={Reinforcement Learning},
pages={143--173},
year={2012},
publisher={Springer}
}
@article{breiman2001random,
title={Random forests},
author={Breiman, Leo},
journal={Machine learning},
volume={45},
number={1},
pages={5--32},
year={2001},
publisher={Springer}
}
@inproceedings{sabatelli2018deep,
title={Deep transfer learning for art classification problems},
author={Sabatelli, Matthia and Kestemont, Mike and Daelemans, Walter and Geurts, Pierre},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
pages={631--646},
year={2018}
}
@inproceedings{sabatelli2020transferability,
title={On the transferability of winning tickets in non-natural image datasets},
author={Sabatelli, Matthia and Kestemont, Mike and Geurts, Pierre},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)},
pages={59--69},
year={2021},
publisher={SciTePress}
}
@article{hessel2019inductive,
title={On inductive biases in deep reinforcement learning},
author={Hessel, Matteo and van Hasselt, Hado and Modayil, Joseph and Silver, David},
journal={arXiv preprint arXiv:1907.02908},
year={2019}
}
@article{tseng2017deep,
title={Deep reinforcement learning for automated radiation adaptation in lung cancer},
author={Tseng, Huan-Hsin and Luo, Yi and Cui, Sunan and Chien, Jen-Tzung and Ten Haken, Randall K and Naqa, Issam El},
journal={Medical physics},
volume={44},
number={12},
pages={6690--6705},
year={2017},
publisher={Wiley Online Library}
}
@article{kalashnikov2018qt,
title={Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation},
author={Kalashnikov, Dmitry and Irpan, Alex and Pastor, Peter and Ibarz, Julian and Herzog, Alexander and Jang, Eric and Quillen, Deirdre and Holly, Ethan and Kalakrishnan, Mrinal and Vanhoucke, Vincent and others},
journal={arXiv preprint arXiv:1806.10293},
year={2018}
}
@article{he2015deep,
title={Deep reinforcement learning with a natural language action space},
author={He, Ji and Chen, Jianshu and He, Xiaodong and Gao, Jianfeng and Li, Lihong and Deng, Li and Ostendorf, Mari},
journal={arXiv preprint arXiv:1511.04636},
year={2015}
}
@article{narasimhan2015language,
title={Language understanding for text-based games using deep reinforcement learning},
author={Narasimhan, Karthik and Kulkarni, Tejas and Barzilay, Regina},
journal={arXiv preprint arXiv:1506.08941},
year={2015}
}
@inproceedings{sutton1999policy,
title={Policy gradient methods for reinforcement learning with function approximation.},
author={Sutton, Richard S and McAllester, David A and Singh, Satinder P and Mansour, Yishay and others},
booktitle={NIPs},
volume={99},
pages={1057--1063},
year={1999},
organization={Citeseer}
}
@article{williams1992simple,
title={Simple statistical gradient-following algorithms for connectionist reinforcement learning},
author={Williams, Ronald J},
journal={Machine learning},
volume={8},
number={3-4},
pages={229--256},
year={1992},
publisher={Springer}
}
@inproceedings{raghu2017continuous,
title={Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach},
author={Raghu, Aniruddh and Komorowski, Matthieu and Celi, Leo Anthony and Szolovits, Peter and Ghassemi, Marzyeh},
booktitle={Machine Learning for Healthcare Conference},
pages={147--163},
year={2017},
organization={PMLR}
}
@article{liu2017learning,
title={Learning to schedule control fragments for physics-based characters using deep q-learning},
author={Liu, Libin and Hodgins, Jessica},
journal={ACM Transactions on Graphics (TOG)},
volume={36},
number={3},
pages={1--14},
year={2017},
publisher={ACM New York, NY, USA}
}
@article{sajedian2020design,
title={Design of high transmission color filters for solar cells directed by deep Q-learning},
author={Sajedian, Iman and Lee, Heon and Rho, Junsuk},
journal={Solar Energy},
volume={195},
pages={670--676},
year={2020},
publisher={Elsevier}
}
@inproceedings{morcos2019one,
title={One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers},
author={Morcos, Ari and Yu, Haonan and Paganini, Michela and Tian, Yuandong},
booktitle={Advances in Neural Information Processing Systems},
pages={4933--4943},
year={2019}
}
@article{yu2019playing,
title={Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP},
author={Yu, Haonan and Edunov, Sergey and Tian, Yuandong and Morcos, Ari S},
journal={arXiv preprint arXiv:1906.02768},
year={2019}
}
@inproceedings{zhou2019deconstructing,
title={Deconstructing lottery tickets: Zeros, signs, and the supermask},
author={Zhou, Hattie and Lan, Janice and Liu, Rosanne and Yosinski, Jason},
booktitle={Advances in Neural Information Processing Systems},
pages={3592--3602},
year={2019}
}
@article{mehta2019sparse,
title={Sparse Transfer Learning via Winning Lottery Tickets},
author={Mehta, Rahul},
journal={arXiv preprint arXiv:1905.07785},
year={2019}
}
@article{frankle2018lottery,
title={The lottery ticket hypothesis: Finding sparse, trainable neural networks},
author={Frankle, Jonathan and Carbin, Michael},
journal={arXiv preprint arXiv:1803.03635},
year={2018}
}
@article{mehta2008transfer,
title={Transfer in variable-reward hierarchical reinforcement learning},
author={Mehta, Neville and Natarajan, Sriraam and Tadepalli, Prasad and Fern, Alan},
journal={Machine Learning},
volume={73},
number={3},
pages={289},
year={2008},
publisher={Springer}
}
@inproceedings{barreto2017successor,
title={Successor features for transfer in reinforcement learning},
author={Barreto, Andr{\'e} and Dabney, Will and Munos, R{\'e}mi and Hunt, Jonathan J and Schaul, Tom and van Hasselt, Hado P and Silver, David},
booktitle={Advances in neural information processing systems},
pages={4055--4065},
year={2017}
}
@inproceedings{han2015learning,
title={Learning both weights and connections for efficient neural network},
author={Han, Song and Pool, Jeff and Tran, John and Dally, William},
booktitle={Advances in neural information processing systems},
pages={1135--1143},
year={2015}
}
@article{frankle2019linear,
title={Linear mode connectivity and the lottery ticket hypothesis},
author={Frankle, Jonathan and Dziugaite, Gintare Karolina and Roy, Daniel M and Carbin, Michael},
journal={arXiv preprint arXiv:1912.05671},
year={2019}
}
@inproceedings{he2016deep,
title={Deep residual learning for image recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={770--778},
year={2016}
}
@article{han2015deep,
title={Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding},
author={Han, Song and Mao, Huizi and Dally, William J},
journal={arXiv preprint arXiv:1510.00149},
year={2015}
}
@inproceedings{zhuang2018discrimination,
title={Discrimination-aware channel pruning for deep neural networks},
author={Zhuang, Zhuangwei and Tan, Mingkui and Zhuang, Bohan and Liu, Jing and Guo, Yong and Wu, Qingyao and Huang, Junzhou and Zhu, Jinhui},
booktitle={Advances in Neural Information Processing Systems},
pages={875--886},
year={2018}
}
@article{franklestabilizing,
title={Stabilizing the Lottery Ticket Hypothesis},
author={Frankle, Jonathan and Dziugaite, G Karolina and Roy, DM and Carbin, M},
journal={arXiv preprint arXiv:1903.01611},
year = {2019}
}
@article{molchanov2016pruning,
title={Pruning convolutional neural networks for resource efficient inference},
author={Molchanov, Pavlo and Tyree, Stephen and Karras, Tero and Aila, Timo and Kautz, Jan},
journal={arXiv preprint arXiv:1611.06440},
year={2016}
}
@inproceedings{hassibi1993optimal,
title={Optimal brain surgeon and general network pruning},
author={Hassibi, Babak and Stork, David G and Wolff, Gregory J},
booktitle={IEEE international conference on neural networks},
pages={293--299},
year={1993},
organization={IEEE}
}
@inproceedings{lecun1990optimal,
title={Optimal brain damage},
author={LeCun, Yann and Denker, John S and Solla, Sara A},
booktitle={Advances in neural information processing systems},
pages={598--605},
year={1990}
}
@article{maree2016collaborative,
title={Collaborative analysis of multi-gigapixel imaging data using Cytomine},
author={Mar{\'e}e, Rapha{\"e}l and Rollus, Lo{\"\i}c and St{\'e}vens, Benjamin and Hoyoux, Renaud and Louppe, Gilles and Vandaele, R{\'e}my and Begon, Jean-Michel and Kainz, Philipp and Geurts, Pierre and Wehenkel, Louis},
journal={Bioinformatics},
volume={32},
number={9},
pages={1395--1401},
year={2016},
publisher={Oxford University Press}
}
@inproceedings{gonthier2018weakly,
title={Weakly supervised object detection in artworks},
author={Gonthier, Nicolas and Gousseau, Yann and Ladjal, Said and Bonfait, Olivier},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
pages={0--0},
year={2018}
}
@inproceedings{redmon2017yolo9000,
title={YOLO9000: better, faster, stronger},
author={Redmon, Joseph and Farhadi, Ali},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={7263--7271},
year={2017}
}
@inproceedings{selvaraju2017grad,
title={Grad-cam: Visual explanations from deep networks via gradient-based localization},
author={Selvaraju, Ramprasaath R and Cogswell, Michael and Das, Abhishek and Vedantam, Ramakrishna and Parikh, Devi and Batra, Dhruv},
booktitle={Proceedings of the IEEE international conference on computer vision},
pages={618--626},
year={2017}
}
@article{lecun1998gradient,
title={Gradient-based learning applied to document recognition},
author={LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
journal={Proceedings of the IEEE},
volume={86},
number={11},
pages={2278--2324},
year={1998},
publisher={Ieee}
}
@inproceedings{chattopadhay2018grad,
title={Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks},
author={Chattopadhay, Aditya and Sarkar, Anirban and Howlader, Prantik and Balasubramanian, Vineeth N},
booktitle={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
pages={839--847},
year={2018},
organization={IEEE}
}
@article{linnainmaa1970representation,
title={The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors},
author={Linnainmaa, Seppo},
journal={Master's Thesis (in Finnish), Univ. Helsinki},
pages={6--7},
year={1970}
}
@article{arun2020assessing,
title={Assessing the (un) trustworthiness of saliency maps for localizing abnormalities in medical imaging},
author={Arun, Nishanth and Gaw, Nathan and Singh, Praveer and Chang, Ken and Aggarwal, Mehak and Chen, Bryan and Hoebel, Katharina and Gupta, Sharut and Patel, Jay and Gidwani, Mishka and others},
journal={arXiv preprint arXiv:2008.02766},
year={2020}
}
@article{saporta2021deep,
title={Deep learning saliency maps do not accurately highlight diagnostically relevant regions for medical image interpretation},
author={Saporta, Adriel and Gui, Xiaotong and Agrawal, Ashwin and Pareek, Anuj and Truong, Steven QH and Nguyen, Chanh DT and Ngo, Van-Doan and Seekins, Jayne and Blankenberg, Francis G and Ng, Andrew and others},
journal={medRxiv},
year={2021},
publisher={Cold Spring Harbor Laboratory Press}
}
@article{simonyan2013deep,
title={Deep inside convolutional networks: Visualising image classification models and saliency maps},
author={Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew},
journal={arXiv preprint arXiv:1312.6034},
year={2013}
}
@inproceedings{alqaraawi2020evaluating,
title={Evaluating saliency map explanations for convolutional neural networks: a user study},
author={Alqaraawi, Ahmed and Schuessler, Martin and Wei{\ss}, Philipp and Costanza, Enrico and Berthouze, Nadia},
booktitle={Proceedings of the 25th International Conference on Intelligent User Interfaces},
pages={275--285},
year={2020}
}
@article{redmon2018yolov3,
title={Yolov3: An incremental improvement},
author={Redmon, Joseph and Farhadi, Ali},
journal={arXiv preprint arXiv:1804.02767},
year={2018}
}
@article{paganini2020bespoke,
title={Bespoke vs. Pr{\^{e}}t-{\`{a}}-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding},
author={Paganini, Michela and Forde, Jessica Zosa},
journal={arXiv preprint arXiv:2007.04091},
year={2020}
}
@inproceedings{nesterov1983method,
title={A method for solving the convex programming problem with convergence rate O (1/k\^{} 2)},
author={Nesterov, Yurii E},
booktitle={Dokl. akad. nauk Sssr},
volume={269},
pages={543--547},
year={1983}
}
@inproceedings{ronneberger2015u,
title={U-net: Convolutional networks for biomedical image segmentation},
author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
booktitle={International Conference on Medical image computing and computer-assisted intervention},
pages={234--241},
year={2015},
organization={Springer}
}
@inproceedings{lin2014microsoft,
title={Microsoft coco: Common objects in context},
author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
booktitle={European conference on computer vision},
pages={740--755},
year={2014},
organization={Springer}
}
@inproceedings{vapnik1992principles,
title={Principles of risk minimization for learning theory},
author={Vapnik, Vladimir},
booktitle={Advances in neural information processing systems},
pages={831--838},
year={1992}
}
@article{gohil2019one,
title={One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers},
author={Gohil, Varun and Narayanan, S Deepak and Jain, Atishay},
journal={ReScience-C},
year={2020}
}
@article{russakovsky2015imagenet,
title={Imagenet large scale visual recognition challenge},
author={Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
journal={International journal of computer vision},
volume={115},
number={3},
pages={211--252},
year={2015},
publisher={Springer}
}
@article{baydin2018automatic,
title={Automatic differentiation in machine learning: a survey},
author={Baydin, Atilim Gunes and Pearlmutter, Barak A and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark},
journal={Journal of machine learning research},
volume={18},
year={2018},
publisher={Journal of Machine Learning Research}
}
@phdthesis{geurts2002contributions,
title={Contributions to decision tree induction: bias/variance tradeoff and time series classification},
author={Geurts, Pierre},
year={2002},
school={ULi{\`e}ge-University of Li{\`e}ge}
}
@book{friedman2001elements,
title={The elements of statistical learning},
author={Friedman, Jerome and Hastie, Trevor and Tibshirani, Robert and others},
volume={1},
number={10},
year={2001},
publisher={Springer series in statistics New York}
}
@article{louppe2014understanding,
title={Understanding random forests: From theory to practice},
author={Louppe, Gilles},
journal={arXiv preprint arXiv:1407.7502},
year={2014}
}
@article{rumelhart1986learning,
title={Learning representations by back-propagating errors},
author={Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J},
journal={nature},
volume={323},
number={6088},
pages={533--536},
year={1986},
publisher={Nature Publishing Group}
}
@article{everingham2010pascal,
title={The pascal visual object classes (voc) challenge},
author={Everingham, Mark and Van Gool, Luc and Williams, Christopher KI and Winn, John and Zisserman, Andrew},
journal={International journal of computer vision},
volume={88},
number={2},
pages={303--338},
year={2010},
publisher={Springer}
}
@article{schmidt2020descending,
title={Descending through a Crowded Valley--Benchmarking Deep Learning Optimizers},
author={Schmidt, Robin M and Schneider, Frank and Hennig, Philipp},
journal={arXiv preprint arXiv:2007.01547},
year={2020}
}
@article{ruder2016overview,
title={An overview of gradient descent optimization algorithms},
author={Ruder, Sebastian},
journal={arXiv preprint arXiv:1609.04747},
year={2016}
}
@article{sun2019learning,
title={Learning Sparse Sharing Architectures for Multiple Tasks},
author={Sun, Tianxiang and Shao, Yunfan and Li, Xiaonan and Liu, Pengfei and Yan, Hang and Qiu, Xipeng and Huang, Xuanjing},
journal={arXiv preprint arXiv:1911.05034},
year={2019}
}
@article{bottou201113,
title={13 the tradeoffs of large-scale learning},
author={Bottou, L{\'e}on and Bousquet, Olivier},
journal={Optimization for machine learning},
pages={351},
year={2011},
publisher={MIT Press}
}
@inproceedings{tan2019review,
title={Review of second-order optimization techniques in artificial neural networks backpropagation},
author={Tan, Hong Hui and Lim, King Hann},
booktitle={IOP Conference Series: Materials Science and Engineering},
volume={495},
number={1},
pages={012003},
year={2019},
organization={IOP Publishing}
}
@article{desai2019evaluating,
title={Evaluating Lottery Tickets Under Distributional Shifts},
author={Desai, Shrey and Zhan, Hongyuan and Aly, Ahmed},
journal={arXiv preprint arXiv:1910.12708},
year={2019}
}
@inproceedings{szegedy2015going,