-
-
Notifications
You must be signed in to change notification settings - Fork 63
/
Copy pathbook.bib
1456 lines (1450 loc) · 63.4 KB
/
book.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
@article{guidotti2022counterfactual,
title={Counterfactual explanations and how to find them: literature review and benchmarking},
author={Guidotti, Riccardo},
journal={Data Mining and Knowledge Discovery},
pages={1--55},
year={2022},
publisher={Springer},
doi = {10.1007/s10618-022-00831-6}
}
@article{gower1971general,
title={A general coefficient of similarity and some of its properties},
author={Gower, John C},
journal={Biometrics},
pages={857--871},
year={1971},
publisher={JSTOR},
doi = {10.2307/2528823}
}
@article{lipton2018mythos,
title={The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery},
author={Lipton, Zachary C},
journal={Queue},
volume={16},
number={3},
pages={31--57},
year={2018},
publisher={ACM New York, NY, USA},
doi = {10.1145/3236386.3241340}
}
@article{guidotti2018survey,
title={A survey of methods for explaining black box models},
author={Guidotti, Riccardo and Monreale, Anna and Ruggieri, Salvatore and Turini, Franco and Giannotti, Fosca and Pedreschi, Dino},
journal={ACM computing surveys (CSUR)},
volume={51},
number={5},
pages={1--42},
year={2018},
publisher={ACM New York, NY, USA},
doi = {10.1145/3236009},
}
@article{groemping2019south,
title = {South German credit data: Correcting a widely used data set},
author = {Groemping, Ulrike},
journal = {Rep. Math., Phys. Chem., Berlin, Germany, Tech. Rep},
volume = {4},
pages = {2019},
year = {2019},
}
@article{molnar2021relating,
title = {Relating the partial dependence plot and permutation feature importance to the data generating process},
author = {Molnar, Christoph and Freiesleben, Timo and K{\"o}nig, Gunnar and Casalicchio, Giuseppe and Wright, Marvin N and Bischl, Bernd},
journal = {arXiv preprint arXiv:2109.01433},
year = {2021},
}
@article{breiman2001random,
title = {Random forests},
author = {Breiman, Leo},
journal = {Machine learning},
volume = {45},
pages = {5--32},
year = {2001},
publisher = {Springer},
doi = {10.1023/A:1010933404324},
}
@article{greenwell2018simple,
title = {A simple and effective model-based variable importance measure},
author = {Greenwell, Brandon M and Boehmke, Bradley C and McCarthy, Andrew J},
journal = {arXiv preprint arXiv:1805.04755},
year = {2018},
}
@misc{lundberg2019consistent,
title = {Consistent Individualized Feature Attribution for Tree Ensembles},
author = {Scott M. Lundberg and Gabriel G. Erion and Su-In Lee},
year = {2019},
eprint = {1802.03888},
archiveprefix = {arXiv},
primaryclass = {cs.LG},
}
@article{bergstra2012,
title = {Random Search for Hyper-Parameter Optimization},
author = {Bergstra, James and Bengio, Yoshua},
publisher = {JMLR.org},
volume = {13},
pages = {281--305},
issn = {1532-4435},
note = {02435},
date = {2012},
journaltitle = {Journal of Machine Learning Research},
url = {https://jmlr.org/papers/v13/bergstra12a.html},
}
@article{chandrashekar2014,
title = {A survey on feature selection methods},
author = {Chandrashekar, Girish and Sahin, Ferat},
volume = {40},
number = {1},
pages = {16--28},
doi = {10.1016/j.compeleceng.2013.11.024},
issn = {0045-7906},
url = {https://www.sciencedirect.com/science/article/pii/S0045790613003066},
note = {40th-year commemorative issue},
date = {2014},
journaltitle = {Computers and Electrical Engineering},
}
@article{Wolpert1992,
title = {Stacked generalization},
author = {Wolpert, David H.},
volume = {5},
number = {2},
pages = {241--259},
doi = {10.1016/S0893-6080(05)80023-1},
issn = {0893-6080},
url = {https://www.sciencedirect.com/science/article/pii/S0893608005800231},
date = {1992},
journaltitle = {Neural Networks},
}
@article{Breiman1996,
title = {Bagging predictors},
author = {Breiman, Leo},
publisher = {Springer},
volume = {24},
number = {2},
pages = {123--140},
date = {1996},
journaltitle = {Machine learning},
doi = {10.1007/BF00058655},
}
@article{Li2016,
title = {Efficient Hyperparameter Optimization and Infinitely Many Armed Bandits},
author = {Lisha Li and Kevin G. Jamieson and Giulia DeSalvo and Afshin Rostamizadeh and Ameet Talwalkar},
year = {2016},
journal = {CoRR},
volume = {abs/1603.06560},
url = {https://arxiv.org/abs/1603.06560},
archiveprefix = {arXiv},
eprint = {1603.06560},
timestamp = {Mon, 13 Aug 2018 16:48:11 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/LiJDRT16},
bibsource = {dblp computer science bibliography, https://dblp.org},
}
@article{mlr3,
title = {{mlr3}: A modern object-oriented machine learning framework in {R}},
author = {Lang, Michel and Binder, Martin and Richter, Jakob and Schratz, Patrick and Pfisterer, Florian and Coors, Stefan and Au, Quay and Casalicchio, Giuseppe and Kotthoff, Lars and Bischl, Bernd},
doi = {10.21105/joss.01903},
url = {https://joss.theoj.org/papers/10.21105/joss.01903},
date = {2019-12},
journaltitle = {Journal of Open Source Software},
}
@article{mlr,
title = {{mlr}: {M}achine {L}earning in {R}},
author = {Bischl, Bernd and Lang, Michel and Kotthoff, Lars and Schiffner, Julia and Richter, Jakob and Studerus, Erich and Casalicchio, Giuseppe and Jones, Zachary M.},
volume = {17},
number = {170},
pages = {1--5},
url = {https://jmlr.org/papers/v17/15-066.html},
date = {2016},
journaltitle = {Journal of Machine Learning Research},
}
@article{caret,
title = {Building Predictive Models in {R} Using the caret Package},
author = {Kuhn, Max},
volume = {28},
number = {5},
pages = {1--26},
doi = {10.18637/jss.v028.i05},
issn = {1548-7660},
url = {https://www.jstatsoft.org/v028/i05},
date = {2008},
journaltitle = {Journal of Statistical Software, Articles},
}
@manual{R,
title = {R: A Language and Environment for Statistical Computing},
author = {{R Core Team}},
location = {Vienna, Austria},
url = {https://www.R-project.org/},
organization = {{R} Foundation for Statistical Computing},
date = {2019},
}
@article{checkmate,
title = {{checkmate}: Fast Argument Checks for Defensive {R} Programming},
author = {Lang, Michel},
volume = {9},
number = {1},
pages = {437--445},
doi = {10.32614/RJ-2017-028},
date = {2017},
journaltitle = {The {R} Journal},
}
@book{Silverman1986,
title = {Density estimation for statistics and data analysis},
author = {Silverman, Bernard W},
year = {1986},
publisher = {CRC press},
volume = {26},
}
@book{Collett2014,
title = {Modelling Survival Data in Medical Research},
author = {Collett, David},
year = {2014},
publisher = {CRC},
isbn = {978-1584883258},
edition = {3},
doi = {10.1201/b18041},
}
@book{MLSA,
author = {Sonabend, Raphael and Bender, Andreas},
title = {Machine Learning in Survival Analysis},
url = {https://www.mlsabook.com},
year = {2023},
}
@phdthesis{Sonabend2021b,
author = {Sonabend, Raphael Edward Benjamin},
pages = {345},
school = {University College London (UCL)},
title = {A Theoretical and Methodological Framework for Machine Learning in Survival Analysis: Enabling Transparent and Accessible Predictive Modelling on Right-Censored Time-to-Event Data},
type = {PhD},
url = {https://discovery.ucl.ac.uk/id/eprint/10129352/},
year = {2021},
}
@book{Kalbfleisch2011,
author = {Kalbfleisch, John D and Prentice, Ross L},
isbn = {1118031237},
publisher = {John Wiley \& Sons},
title = {The statistical analysis of failure time data},
volume = {360},
year = {2011},
doi = {10.1002/9781118032985},
}
@article{Sonabend2022,
author = {Sonabend, Raphael and Bender, Andreas and Vollmer, Sebastian},
editor = {Lu, Zhiyong},
issn = {1367-4803},
journal = {Bioinformatics},
month = {sep},
number = {17},
pages = {4178--4184},
title = {Avoiding {C}-hacking when evaluating survival distribution predictions with discrimination measures},
doi = {10.1093/bioinformatics/btac451},
volume = {38},
year = {2022},
}
@book{hastie2001,
doi = {10.1007/978-0-387-21606-5},
year = {2001},
publisher = {Springer New York},
author = {Trevor Hastie and Jerome Friedman and Robert Tibshirani},
title = {The Elements of Statistical Learning},
}
@book{provost2013,
title={Data Science for Business: What you need to know about data mining and data-analytic thinking},
author={Provost, Foster and Fawcett, Tom},
year={2013},
publisher={O'Reilly Media},
}
@inproceedings{brenning2012,
doi = {10.1109/igarss.2012.6352393},
year = {2012},
month = {jul},
publisher = {{IEEE}},
author = {Alexander Brenning},
title = {Spatial cross-validation and bootstrap for the assessment of prediction rules in remote sensing: The {R} package sperrorest},
booktitle = {2012 {IEEE} International Geoscience and Remote Sensing Symposium},
}
@article{schratz2019,
doi = {10.1016/j.ecolmodel.2019.06.002},
year = {2019},
month = {aug},
publisher = {Elsevier {BV}},
volume = {406},
pages = {109--120},
author = {Patrick Schratz and Jannes Muenchow and Eugenia Iturritxa and Jakob Richter and Alexander Brenning},
title = {Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data},
journal = {Ecological Modelling},
}
@article{muenchow2012,
title = {Geomorphic process rates of landslides along a humidity gradient in the tropical Andes},
journal = {Geomorphology},
volume = {139-140},
pages = {271--284},
year = {2012},
issn = {0169-555X},
doi = {10.1016/j.geomorph.2011.10.029},
url = {https://www.sciencedirect.com/science/article/pii/S0169555X11005551},
author = {J. Muenchow and A. Brenning and M. Richter},
keywords = {Mass movements, Denudation rate, Geomorphic work, Generalized additive model},
}
@book{lovelace2019,
title = {Geocomputation with {R}},
author = {Lovelace, Robin and Nowosad, Jakub and Muenchow, Jannes},
year = {2019},
publisher = {CRC Press},
}
@article{legendre1993,
doi = {10.2307/1939924},
year = {1993},
month = {sep},
publisher = {Wiley},
volume = {74},
number = {6},
pages = {1659--1673},
author = {Pierre Legendre},
title = {Spatial Autocorrelation: Trouble or New Paradigm?},
journal = {Ecology},
}
@article{guyon2003,
title = {An introduction to variable and feature selection},
author = {Guyon, Isabelle and Elisseeff, Andr{\'e}},
journal = {Journal of machine learning research},
volume = {3},
number = {Mar},
pages = {1157--1182},
year = {2003},
url = {https://www.jmlr.org/papers/v3/guyon03a.html},
}
@incollection{Simon2007,
title = {Resampling Strategies for Model Assessment and Selection},
booktitle = {Fundamentals of Data Mining in Genomics and Proteomics},
author = {Simon, Richard},
editor = {Dubitzky, Werner and Granzow, Martin and Berrar, Daniel},
date = {2007},
pages = {173--186},
publisher = {{Springer US}},
location = {{Boston, MA}},
doi = {10.1007/978-0-387-47509-7_8},
isbn = {978-0-387-47509-7},
}
@article{bischl2012resampling,
title = {Resampling methods for meta-model validation with recommendations for evolutionary computation},
author = {Bischl, Bernd and Mersmann, Olaf and Trautmann, Heike and Weihs, Claus},
journal = {Evolutionary computation},
volume = {20},
number = {2},
pages = {249--275},
year = {2012},
publisher = {MIT Press},
doi = {10.1162/EVCO_a_00069 },
}
@article{mlr3pipelines,
title = {{mlr3pipelines} - Flexible Machine Learning Pipelines in {R}},
author = {Martin Binder and Florian Pfisterer and Michel Lang and Lennart Schneider and Lars Kotthoff and Bernd Bischl},
journal = {Journal of Machine Learning Research},
year = {2021},
volume = {22},
number = {184},
pages = {1--7},
url = {https://jmlr.org/papers/v22/21-0281.html},
}
@article{mlr3proba,
title = {{mlr3proba}: An {R} Package for Machine Learning in Survival Analysis},
author = {Raphael Sonabend and Franz J Kir\'{a}ly and Andreas Bender and Bernd Bischl and Michel Lang},
journal = {Bioinformatics},
month = {02},
year = {2021},
doi = {10.1093/bioinformatics/btab039},
issn = {1367-4803},
}
@inproceedings{Thornton2013,
doi = {10.1145/2487575.2487629},
year = {2013},
month = aug,
publisher = {{ACM}},
author = {Chris Thornton and Frank Hutter and Holger H. Hoos and Kevin Leyton-Brown},
title = {Auto-{WEKA}},
booktitle = {Proceedings of the 19th {ACM} {SIGKDD} international conference on Knowledge discovery and data mining},
}
@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},
doi = {10.1109/5.726791},
}
@article{meyer2018,
title = {Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation},
author = {Meyer, Hanna and Reudenbach, Christoph and Hengl, Tomislav and Katurji, Marwan and Nauss, Thomas},
year = {2018},
month = mar,
journal = {Environmental Modelling \& Software},
volume = {101},
pages = {1--9},
issn = {1364-8152},
doi = {10.1016/j.envsoft.2017.12.001},
abstract = {Importance of target-oriented validation strategies for spatio-temporal prediction models is illustrated using two case studies: (1) modelling of air temperature (Tair) in Antarctica, and (2) modelling of volumetric water content (VW) for the R.J. Cook Agronomy Farm, USA. Performance of a random k-fold cross-validation (CV) was compared to three target-oriented strategies: Leave-Location-Out (LLO), Leave-Time-Out (LTO), and Leave-Location-and-Time-Out (LLTO) CV. Results indicate that considerable differences between random k-fold (R2~=~0.9 for Tair and 0.92 for VW) and target-oriented CV (LLO R2~=~0.24 for Tair and 0.49 for VW) exist, highlighting the need for target-oriented validation to avoid an overoptimistic view on models. Differences between random k-fold and target-oriented CV indicate spatial over-fitting caused by misleading variables. To decrease over-fitting, a forward feature selection in conjunction with target-oriented CV is proposed. It decreased over-fitting and simultaneously improved target-oriented performances (LLO CV R2~=~0.47 for Tair and 0.55 for VW).},
langid = {english},
keywords = {Cross-validation,Feature selection,Over-fitting,Random forest,Spatio-temporal,Target-oriented validation},
}
@article{openml2013,
author = {Joaquin Vanschoren and Jan N. van Rijn and Bernd Bischl and Luis Torgo},
title = {OpenML: networked science in machine learning},
journal = {SIGKDD Explorations},
volume = {15},
number = {2},
year = {2013},
pages = {49--60},
doi = {10.1145/2641190.2641198},
publisher = {ACM},
}
@article{demsar2006,
author = {Janez Dem\v{s}ar},
title = {Statistical Comparisons of Classifiers over Multiple Data Sets},
journal = {Journal of Machine Learning Research},
year = {2006},
volume = {7},
number = {1},
pages = {1--30},
url = {https://jmlr.org/papers/v7/demsar06a.html},
}
@article{hpo_practical,
title = {Hyperparameter Optimization: Foundations, Algorithms, Best Practices, and Open Challenges},
author = {Bischl, Bernd and Binder, Martin and Lang, Michel and Pielok, Tobias and Richter, Jakob and Coors, Stefan and Thomas, Janek and Ullmann, Theresa and Becker, Marc and Boulesteix, Anne-Laure and Deng, Difan and Lindauer, Marius},
journal = {Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery},
doi = {10.1002/widm.1484},
pages = {e1484},
year = {2023},
publisher = {Wiley Online Library},
}
@article{dobbin2011,
title = {Optimally Splitting Cases for Training and Testing High Dimensional Classifiers},
author = {Dobbin, Kevin K. and Simon, Richard M.},
date = {2011-04-08},
journaltitle = {BMC Medical Genomics},
shortjournal = {BMC Medical Genomics},
volume = {4},
number = {1},
pages = {31},
issn = {1755-8794},
doi = {10.1186/1755-8794-4-31},
urldate = {2023-03-17},
keywords = {Full Dataset,Isotonic Regression,Mean Square Error,Supplemental Section,Training Sample Size},
}
@inproceedings{kohavi1995,
title = {A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection},
booktitle = {Proceedings of the 14th International Joint Conference on {{Artificial}} Intelligence - {{Volume}} 2},
author = {Kohavi, Ron},
date = {1995-08-20},
series = {{{IJCAI}}'95},
pages = {1137--1143},
publisher = {{Morgan Kaufmann Publishers Inc.}},
location = {{San Francisco, CA, USA}},
isbn = {978-1-55860-363-9},
}
@article{bommert2020,
title = {Benchmark for filter methods for feature selection in high-dimensional classification data},
journal = {Computational Statistics \& Data Analysis},
volume = {143},
pages = {106839},
year = {2020},
issn = {0167-9473},
doi = {10.1016/j.csda.2019.106839},
url = {https://www.sciencedirect.com/science/article/pii/S016794731930194X},
author = {Andrea Bommert and Xudong Sun and Bernd Bischl and J\"{o}rg Rahnenf\"{u}hrer and Michel Lang},
}
@inbook{hpo_automl,
author = {Feurer, Matthias and Hutter, Frank},
editor = {Hutter, Frank and Kotthoff, Lars and Vanschoren, Joaquin},
title = {Hyperparameter Optimization},
booktitle = {Automated Machine Learning: Methods, Systems, Challenges},
year = {2019},
publisher = {Springer International Publishing},
address = {Cham},
pages = {3--33},
doi = {10.1007/978-3-030-05318-5_1},
}
@inproceedings{hansen2011,
title = {CMA-ES: evolution strategies and covariance matrix adaptation},
author = {Hansen, Nikolaus and Auger, Anne},
booktitle = {Proceedings of the 13th annual conference companion on Genetic and evolutionary computation},
pages = {991--1010},
year = {2011},
doi = {10.1145/2001858.2002123}
}
@article{xiang2013,
title = {Generalized simulated annealing for global optimization: the GenSA package.},
author = {Xiang, Yang and Gubian, Sylvain and Suomela, Brian and Hoeng, Julia},
journal = {{R} Journal},
volume = {5},
number = {1},
pages = {13},
year = {2013},
doi = {10.32614/RJ-2013-002},
}
@article{tsallis1996,
title = {Generalized simulated annealing},
author = {Tsallis, Constantino and Stariolo, Daniel A},
journal = {Physica A: Statistical Mechanics and its Applications},
volume = {233},
number = {1-2},
pages = {395--406},
year = {1996},
publisher = {Elsevier},
doi = {10.1016/S0378-4371(96)00271-3},
}
@article{lopez2016,
title = {The {irace} package: Iterated racing for automatic algorithm configuration},
author = {L{\'o}pez-Ib{\'a}{\~n}ez, Manuel and Dubois-Lacoste, J{\'e}r{\'e}mie and C{\'a}ceres, Leslie P{\'e}rez and Birattari, Mauro and St{\"u}tzle, Thomas},
journal = {Operations Research Perspectives},
volume = {3},
pages = {43--58},
year = {2016},
publisher = {Elsevier},
doi = {10.1016/j.orp.2016.09.002},
}
@book{james_introduction_2014,
author = {James, Gareth and Witten, Daniela and Hastie, Trevor and Tibshirani, Robert},
title = {An Introduction to Statistical Learning: With Applications in {R}},
year = {2014},
isbn = {1461471370},
publisher = {Springer Publishing Company, Incorporated},
doi = {10.1007/978-1-4614-7138-7},
}
@book{japkowicz2011evaluating,
title = {Evaluating learning algorithms: a classification perspective},
author = {Japkowicz, Nathalie and Shah, Mohak},
year = {2011},
publisher = {Cambridge University Press},
doi = {10.1017/CBO9780511921803},
}
@article{bengio2003no,
title = {No unbiased estimator of the variance of k-fold cross-validation},
author = {Bengio, Yoshua and Grandvalet, Yves},
journal = {Advances in Neural Information Processing Systems},
volume = {16},
year = {2003},
}
@article{molinaro2005prediction,
title = {Prediction error estimation: a comparison of resampling methods},
author = {Molinaro, Annette M and Simon, Richard and Pfeiffer, Ruth M},
journal = {Bioinformatics},
volume = {21},
number = {15},
pages = {3301--3307},
year = {2005},
publisher = {Oxford University Press},
doi = {10.1093/bioinformatics/bti499},
}
@article{kim2009estimating,
title = {Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap},
author = {Kim, Ji-Hyun},
journal = {Computational statistics \& data analysis},
volume = {53},
number = {11},
pages = {3735--3745},
year = {2009},
publisher = {Elsevier},
doi = {10.1016/j.csda.2009.04.009},
}
@book{biecek_burzykowski_2021,
author = {Przemyslaw Biecek and Tomasz Burzykowski},
title = {Explanatory Model Analysis},
year = {2021},
isbn = {9780367135591},
url = {https://ema.drwhy.ai/},
publisher = {Chapman and Hall/CRC, New York},
}
@book{ONeil,
title = {Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy},
author = {O'Neil, Cathy},
year = {2016},
publisher = {Crown Publishing Group},
address = {New York, NY},
isbn = {0553418815, 9780553418811},
}
@article{Molnar2018,
author = {Christoph Molnar and Bernd Bischl and Giuseppe Casalicchio},
title = {{iml}: An {R} package for Interpretable Machine Learning},
doi = {10.21105/joss.00786},
url = {https://joss.theoj.org/papers/10.21105/joss.00786},
year = {2018},
publisher = {Journal of Open Source Software},
volume = {3},
number = {26},
pages = {786},
journal = {JOSS},
}
@book{Molnar2022,
title = {Interpretable Machine Learning},
author = {Christoph Molnar},
year = {2022},
subtitle = {A Guide for Making Black Box Models Explainable},
edition = {2},
url = {https://christophm.github.io/interpretable-ml-book},
}
@article{Fisher2019pfi,
title = {All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously},
author = {Aaron Fisher and Cynthia Rudin and Francesca Dominici},
year = {2019},
doi = {10.48550/arxiv.1801.01489},
publisher = {arXiv},
url = {https://arxiv.org/abs/1801.01489},
}
@article{Friedman2001pdp,
doi = {10.1214/aos/1013203451},
year = {2001},
month = oct,
publisher = {Institute of Mathematical Statistics},
volume = {29},
number = {5},
author = {Jerome H. Friedman},
title = {Greedy function approximation: A gradient boosting machine.},
journal = {The Annals of Statistics},
}
@article{Goldstein2015ice,
doi = {10.1080/10618600.2014.907095},
year = {2015},
month = jan,
publisher = {Informa {UK} Limited},
volume = {24},
number = {1},
pages = {44--65},
author = {Alex Goldstein and Adam Kapelner and Justin Bleich and Emil Pitkin},
title = {Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation},
journal = {Journal of Computational and Graphical Statistics},
}
@inproceedings{Ribeiro2016lime,
title = {{``}Why Should {I} Trust You?{''}: Explaining the Predictions of Any Classifier},
author = {Ribeiro, Marco and Singh, Sameer and Guestrin, Carlos},
booktitle = {Proceedings of the 2016 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Demonstrations},
month = jun,
year = {2016},
address = {San Diego, California},
publisher = {Association for Computational Linguistics},
doi = {10.18653/v1/N16-3020},
pages = {97--101},
}
@article{Trumbelj2013Shapley,
doi = {10.1007/s10115-013-0679-x},
year = {2013},
month = aug,
publisher = {Springer Science and Business Media {LLC}},
volume = {41},
number = {3},
pages = {647--665},
author = {Erik {\v{S}}trumbelj and Igor Kononenko},
title = {Explaining prediction models and individual predictions with feature contributions},
journal = {Knowledge and Information Systems},
}
@article{Wachter2017,
doi = {10.2139/ssrn.3063289},
year = {2017},
publisher = {Elsevier {BV}},
author = {Sandra Wachter and Brent Mittelstadt and Chris Russell},
title = {Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the {GDPR}},
journal = {{SSRN} Electronic Journal},
}
@article{Wachter2021,
title = {Why fairness cannot be automated: Bridging the gap between EU non-discrimination law and AI},
journal = {Computer Law & Security Review},
volume = {41},
pages = {105567},
year = {2021},
issn = {0267-3649},
doi = {https://doi.org/10.1016/j.clsr.2021.105567},
url = {https://www.sciencedirect.com/science/article/pii/S0267364921000406},
author = {Sandra Wachter and Brent Mittelstadt and Chris Russell}
}
@article{Wexler2019,
author = {Wexler, James and Pushkarna, Mahima and Bolukbasi, Tolga and Wattenberg, Martin and Vi{\'e}gas, Fernanda and Wilson, Jimbo},
journal = {IEEE transactions on visualization and computer graphics},
title = {The What-If Tool: Interactive Probing of Machine Learning Models},
year = {2019},
number = {1},
pages = {56--65},
volume = {26},
publisher = {IEEE},
doi = {10.1109/TVCG.2019.2934619},
}
@incollection{Dandl2020,
doi = {10.1007/978-3-030-58112-1_31},
year = {2020},
publisher = {Springer International Publishing},
pages = {448--469},
author = {Susanne Dandl and Christoph Molnar and Martin Binder and Bernd Bischl},
title = {Multi-Objective Counterfactual Explanations},
booktitle = {Parallel Problem Solving from Nature {PPSN} {XVI}},
}
@article{Hooker2019PleaseSP,
title = {Please Stop Permuting Features: An Explanation and Alternatives},
author = {Giles Hooker and Lucas K. Mentch},
year = {2019},
doi = {10.48550/arxiv.1905.03151},
publisher = {arXiv},
url = {https://arxiv.org/abs/1905.03151},
}
@misc{Lundberg2019,
title = {Consistent Individualized Feature Attribution for Tree Ensembles},
author = {Scott M. Lundberg and Gabriel G. Erion and Su-In Lee},
year = {2019},
doi = {10.48550/arxiv.1802.03888},
publisher = {arXiv},
url = {https://arxiv.org/abs/1802.03888},
}
@article{Au2022,
doi = {10.1007/s10618-022-00840-5},
year = {2022},
month = jun,
publisher = {Springer Science and Business Media {LLC}},
volume = {36},
number = {4},
pages = {1401--1450},
author = {Quay Au and Julia Herbinger and Clemens Stachl and Bernd Bischl and Giuseppe Casalicchio},
title = {Grouped feature importance and combined features effect plot},
journal = {Data Mining and Knowledge Discovery},
}
@article{Breiman2001,
doi = {10.1214/ss/1009213726},
year = {2001},
month = aug,
publisher = {Institute of Mathematical Statistics},
volume = {16},
number = {3},
author = {Leo Breiman},
title = {Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)},
journal = {Statistical Science},
}
@article{Strobl2008,
doi = {10.1186/1471-2105-9-307},
year = {2008},
month = jul,
publisher = {Springer Science and Business Media {LLC}},
volume = {9},
number = {1},
author = {Carolin Strobl and Anne-Laure Boulesteix and Thomas Kneib and Thomas Augustin and Achim Zeileis},
title = {Conditional variable importance for random forests},
journal = {{BMC} Bioinformatics},
}
@article{Apley2020,
doi = {10.1111/rssb.12377},
year = {2020},
month = jun,
publisher = {Oxford University Press ({OUP})},
volume = {82},
number = {4},
pages = {1059--1086},
author = {Daniel W. Apley and Jingyu Zhu},
title = {Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models},
journal = {Journal of the Royal Statistical Society Series B: Statistical Methodology},
}
@inbook{Molnar2022pitfalls,
author = {Molnar, Christoph and K{\"o}nig, Gunnar and Herbinger, Julia and Freiesleben, Timo and Dandl, Susanne and Scholbeck, Christian A. and Casalicchio, Giuseppe and Grosse-Wentrup, Moritz and Bischl, Bernd},
editor = {Holzinger, Andreas and Goebel, Randy and Fong, Ruth and Moon, Taesup and M{\"u}ller, Klaus-Robert and Samek, Wojciech},
title = {General Pitfalls of~Model-Agnostic Interpretation Methods for~Machine Learning Models},
booktitle = {xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers},
year = {2022},
publisher = {Springer International Publishing},
address = {Cham},
pages = {39--68},
doi = {10.1007/978-3-031-04083-2_4},
}
@article{Romaszko2019,
title = {modelDown: automated website generator with interpretable documentation for predictive machine learning models},
author = {Kamil Romaszko and Magda Tatarynowicz and Mateusz Urba\'{n}ski and Przemys\l{}aw Biecek},
year = {2019},
doi = {10.21105/joss.01444},
publisher = {The Open Journal},
volume = {4},
number = {38},
pages = {1444},
journal = {Journal of Open Source Software},
}
@article{Biecek2018,
title = {{DALEX}: Explainers for complex predictive models in {R}},
author = {Biecek, Przemyslaw},
year = {2018},
journal = {Journal of Machine Learning Research},
volume = {19},
number = {84},
pages = {1--5},
url = {https://jmlr.org/papers/v19/18-416.html},
}
@article{Baniecki2021,
author = {Baniecki, Hubert and Kretowicz, Wojciech and Pi\k{a}tyszek, Piotr and Wi\'{s}niewski, Jakub and Biecek, Przemys\l{}aw},
title = {{dalex}: Responsible Machine Learning with Interactive Explainability and Fairness in Python},
journal = {Journal of Machine Learning Research},
year = {2021},
volume = {22},
number = {214},
pages = {1--7},
url = {https://jmlr.org/papers/v22/20-1473.html},
}
@article{Baniecki2023,
title = {The grammar of interactive explanatory model analysis},
author = {Baniecki, Hubert and Parzych, Dariusz and Biecek, Przemyslaw},
journal = {Data Mining and Knowledge Discovery},
doi = {10.1007/s10618-023-00924-w},
year = {2023},
publisher = {Springer},
pages = {1573--756X},
}
@article{Baniecki2019,
title = {{modelStudio}: Interactive Studio with Explanations for ML Predictive Models},
author = {Baniecki, Hubert and Biecek, Przemyslaw},
journal = {Journal of Open Source Software},
doi = {10.21105/joss.01798},
year = {2019},
publisher = {The Open Journal},
volume = {4},
number = {43},
pages = {1798},
}
@article{Holzinger2022,
title = {Explainable AI Methods - A Brief Overview},
author = {Holzinger, Andreas and Saranti, Anna and Molnar, Christoph and Biecek, Przemyslaw and Samek, Wojciech},
year = {2022},
journal = {International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers},
publisher = {Springer International Publishing},
address = {Cham},
pages = {13--38},
doi = {10.1007/978-3-031-04083-2_2},
}
@article{Bucker2022,
author = {B\"{u}cker, Michael and Szepannek, Gero and Gosiewska, Alicja and Biecek, Przemyslaw},
title = {Transparency, auditability, and explainability of machine learning models in credit scoring},
journal = {Journal of the Operational Research Society},
volume = {73},
number = {1},
pages = {70--90},
year = {2022},
publisher = {Taylor \& Francis},
doi = {10.1080/01605682.2021.1922098},
}
@article{Wisniewski2022,
author = {Wi\'{s}niewski, Jakub and Biecek, Przemys\l{}aw},
title = {The {R} Journal: fairmodels: a Flexible Tool for Bias Detection, Visualization, and Mitigation in Binary Classification Models},
journal = {The {R} Journal},
year = {2022},
doi = {10.32614/RJ-2022-019},
volume = {14},
issue = {1},
issn = {2073-4859},
pages = {227--243},
}
@article{Krzyzinski2023,
title = {{SurvSHAP(t)}: Time-dependent explanations of machine learning survival models},
author = {Krzyzi\'{n}ski, Mateusz and Spytek, Miko\l{}aj and Baniecki, Hubert and Biecek, Przemys\l{}aw},
journal = {Knowledge-Based Systems},
volume = {262},
pages = {110234},
year = {2023},
issn = {0950-7051},
doi = {10.1016/j.knosys.2022.110234},
url = {https://www.sciencedirect.com/science/article/pii/S0950705122013302},
}
@manual{palmerpenguins2020,
title = {{palmerpenguins}: Palmer Archipelago (Antarctica) penguin data},
author = {Allison Marie Horst and Alison Presmanes Hill and Kristen B Gorman},
year = {2020},
note = {{R} package version 0.1.0},
doi = {10.5281/zenodo.3960218},
url = {https://allisonhorst.github.io/palmerpenguins/},
}
@manual{Rcore2022,
title = {R: A Language and Environment for Statistical Computing},
author = {{{R} Core Team}},
organization = {{R} Foundation for Statistical Computing},
address = {Vienna, Austria},
year = {2022},
url = {https://www.R-project.org/},
}
@article{hand2001simple,
title = {A simple generalisation of the area under the ROC curve for multiple class classification problems},
author = {Hand, David J and Till, Robert J},
journal = {Machine learning},
volume = {45},
pages = {171--186},
year = {2001},
publisher = {Springer},
doi = {10.1023/A:1010920819831},
}
@inproceedings{davis2006relationship,
title = {The relationship between Precision-Recall and ROC curves},
author = {Davis, Jesse and Goadrich, Mark},
booktitle = {Proceedings of the 23rd international conference on Machine learning},
pages = {233--240},
year = {2006},
doi = {10.1145/1143844.1143874},
}
@book{bishop_2006,
author = {Bishop, Christopher M.},
title = {Pattern Recognition and Machine Learning},
year = {2006},
publisher = {Springer},
}
@book{garnett_2022,
author = {Garnett, Roman},
title = {Bayesian Optimization},
year = {2022},
publisher = {Cambridge University Press},
note = {in preparation},
url = {https://bayesoptbook.com/},
}
@article{jones_1998,
title = {Efficient Global Optimization of Expensive Black-Box Functions},
volume = {13},
number = {4},
journal = {Journal of Global Optimization},
author = {Jones, Donald R. and Schonlau, Matthias and Welch, William J.},
year = {1998},
pages = {455--492},
doi = {10.1023/A:1008306431147},
}
@book{williams_2006,
title = {Gaussian Processes for Machine Learning},
author = {Williams, Christopher KI and Rasmussen, Carl Edward},
volume = {2},
number = {3},
year = {2006},
publisher = {MIT press Cambridge, MA},
}
@article{knowles_2006,
title = {ParEGO: A Hybrid Algorithm With On-Line Landscape Approximation for Expensive Multiobjective Optimization Problems},
volume = {10},
number = {1},
journal = {IEEE Transactions on Evolutionary Computation},
author = {Knowles, Joshua},
year = {2006},
pages = {50--66},
doi = {10.1109/TEVC.2005.851274},
}
@inproceedings{ponweiser_2008,
title = {Multiobjective Optimization on a Limited Budget of Evaluations Using Model-Assisted S-Metric Selection},
author = {Ponweiser, Wolfgang and Wagner, Tobias and Biermann, Dirk and Vincze, Markus},
year = {2008},
booktitle = {Proceedings of the 10th International Conference on Parallel Problem Solving from Nature},
pages = {784--794},
}
@article{huang_2012,
title = {Erratum To: Global Optimization of Stochastic Black-box Systems via Sequential Kriging Meta-Models},
author = {D. Huang and T. T. Allen and W. I. Notz and N. Zheng},
year = {2012},
volume = {54},
number = {2},
pages = {431--431},
journal = {Journal of Global Optimization},
doi = {10.1007/s10898-011-9821-z},
}
@article{li_2018,
author = {Lisha Li and Kevin Jamieson and Giulia DeSalvo and Afshin Rostamizadeh and Ameet Talwalkar},
title = {Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization},
journal = {Journal of Machine Learning Research},
year = {2018},
volume = {18},
number = {185},
pages = {1--52},
url = {https://jmlr.org/papers/v18/16-558.html},
}
@inproceedings{jamieson_2016,
title = {Non-stochastic Best Arm Identification and Hyperparameter Optimization},
author = {Kevin Jamieson and Ameet Talwalkar},
booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics},
pages = {240--248},
year = {2016},
editor = {Arthur Gretton and Christian C. Robert},
volume = {51},
series = {Proceedings of Machine Learning Research},
address = {Cadiz, Spain},
publisher = {PMLR},
url = {https://proceedings.mlr.press/v51/jamieson16.html},
}
@inproceedings{binder2020,
title = {Collecting Empirical Data About Hyperparameters for Data Driven AutoML},
author = {Martin Binder and Florian Pfisterer and Bernd Bischl},
url = {https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_63.pdf},
year = {2020},
booktitle = {Proceedings of the 7th ICML Workshop on Automated Machine Learning (AutoML 2020)},
date = {2020-07-18},
tag = {Optim},
}
@misc{kuehn_2018,
title = {Automatic Exploration of Machine Learning Experiments on OpenML},
author = {Daniel Kuehn and Philipp Probst and Janek Thomas and Bernd Bischl},
year = {2018},
eprint = {1806.10961},
archiveprefix = {arXiv},
primaryclass = {stat.ML},
url = {https://arxiv.org/abs/1806.10961},
}
@article{Schratz2021,
archiveprefix = {arXiv},
arxivid = {2110.12674},
author = {Schratz, Patrick and Becker, Marc and Lang, Michel and Brenning, Alexander},
eprint = {2110.12674},
month = {oct},
title = {{mlr3spatiotempcv}: Spatiotemporal resampling methods for machine learning in {R}},
url = {https://arxiv.org/abs/2110.12674},
year = {2021},
}
@article{Ruspini1970,
title = {Numerical methods for fuzzy clustering},
journal = {Information Sciences},
volume = {2},
number = {3},
pages = {319--350},