{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T22:15:26Z","timestamp":1777760126905,"version":"3.51.4"},"reference-count":211,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3220744","type":"journal-article","created":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T20:41:18Z","timestamp":1668026478000},"page":"7799-7819","source":"Crossref","is-referenced-by-count":120,"title":["The Shape of Learning Curves: A Review"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-8624","authenticated-orcid":false,"given":"Tom","family":"Viering","sequence":"first","affiliation":[{"name":"Delft University of Technology, Delft, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1298-8461","authenticated-orcid":false,"given":"Marco","family":"Loog","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, The Netherlands"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"\u00dcber Das Ged\u00e4chtnis: Untersuchungen Zur Experimentellen Psychologie","author":"Ebbinghaus","year":"1885"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5915.1979.tb00026.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ergon.2011.05.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/34.824819"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-811788-0.00005-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/j.1751-5823.2000.tb00332.x"},{"key":"ref7","first-page":"3460","article-title":"Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves","volume-title":"Proc. 24th Int. Conf. Artif. Intell.","author":"Domhan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_452"},{"key":"ref9","volume-title":"Encyclopedia of Machine Learning","author":"Sammut","year":"2011"},{"key":"ref10","article-title":"A modification of veto logic for a committee of threshold logic units and the use of 2-class classifiers for function estimation","author":"Osborne","year":"1975"},{"key":"ref11","first-page":"566","article-title":"Training connectionist networks with queries and selective sampling","volume-title":"Proc. 2nd Int. Conf. Neural Inf. Process. Syst.","author":"Atlas"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.65.1683"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/h0073806"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1037\/h0062885"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1412713"},{"key":"ref16","first-page":"195","article-title":"Der einfluss der einzelnen wiederholungen auf verschieden starke und verschieden alte associationen","volume":"35","author":"Lipmann","year":"1904","journal-title":"Z. Psychol. Physiol. Si."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S0031819100051743"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1972.1054863"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PGEC.1965.264137"},{"key":"ref21","volume-title":"Pattern Classification","author":"Duda","year":"2012"},{"key":"ref22","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"ref23","volume-title":"Semi-Supervised Learning","author":"Chapelle","year":"2010"},{"key":"ref24","article-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1089\/106652703321825928"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00135"},{"key":"ref28","first-page":"841","article-title":"On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes","volume-title":"Proc. 14th Int. Conf. Neural Inf. Process. Syst.","author":"Ng"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2009.04.009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1053\/j.seminoncol.2009.12.002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2288636"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767957"},{"issue":"1","key":"ref36","first-page":"211","article-title":"Tree Induction vs. Logistic regression: A learning-curve analysis","volume":"4","author":"Perlich","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/312129.312188"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50062-1"},{"key":"ref39","article-title":"Active learning in the presence of unlabelable examples","author":"Mazzoni","year":"2004","journal-title":"Proc. Eur. Conf. Mach. Learn."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613855"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/00221309.1937.9917971"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115008"},{"key":"ref43","first-page":"433","article-title":"Evaluating the learning curve of domain adaptive statistical machine translation systems","volume-title":"Proc. Workshop Statist. Mach. Transl.","author":"Bertoldi"},{"key":"ref44","first-page":"4287","article-title":"Learning curves for analysis of deep networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Hoiem"},{"key":"ref45","first-page":"327","article-title":"Learning curves: Asymptotic values and rate of convergence","volume-title":"Proc. 6th Int. Conf. Neural Inf. Process. Syst.","author":"Cortes"},{"key":"ref46","first-page":"59","article-title":"Modeling decision tree performance with the power law","volume-title":"Proc. 7th Int. Workshop Artif. Intell. Statist.","author":"Frey"},{"key":"ref47","article-title":"Modeling performance of different classification methods: Deviation from the power law","author":"Singh","year":"2005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2007.31"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47714-4_29"},{"key":"ref50","first-page":"22","article-title":"Prediction of learning curves in machine translation","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguistics","author":"Kolachina"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054102"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/s0169-7161(82)02042-2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/34.75512"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(97)00138-4"},{"key":"ref55","first-page":"118","article-title":"Kernel regression trees","volume-title":"Proc. Eur. Conf. Mach. Learn.","author":"Torgo"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1142\/9789812775320_0001"},{"key":"ref58","article-title":"Multiple descent: Design your own generalization curve","author":"Chen","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1978.4309980"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/s0169-7161(82)02042-2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1980.4767011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/9\/4\/003"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.906006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s00357-019-09327-3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/23\/11\/012"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.65.499"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139164542"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(78)90008-0"},{"key":"ref70","article-title":"On the accuracy of statistical pattern recognizers","author":"Duin","year":"1978"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1996.547204"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1976.1674577"},{"key":"ref73","article-title":"A constructive prediction of the generalization error across scales","author":"Rosenfeld","year":"2019"},{"key":"ref74","article-title":"Learning curves for decision making in supervised machine learning\u2013A survey","author":"Mohr","year":"2022"},{"key":"ref76","article-title":"Winners curse? On pace, progress, and empirical rigor","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sculley"},{"key":"ref77","article-title":"A critical analysis of metrics used for measuring progress in artificial intelligence","author":"Blagec","year":"2020"},{"key":"ref78","first-page":"64","article-title":"On the problems of sample size in pattern recognition (in Russian)","volume-title":"Proc. 2nd All-Union Conf. Statist. Meth. Contr. Theory","author":"Raudys"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(71)90013-6"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(98)00016-6"},{"key":"ref81","first-page":"202","article-title":"Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid","volume-title":"Proc. 2nd Int. Conf. Knowl. Discov. Data Mining","author":"Kohavi"},{"key":"ref82","article-title":"Small data, big decisions: Model selection in the small-data regime","author":"Bornschein","year":"2020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01768-2_25"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63046-5_20"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114160"},{"issue":"2\/3","key":"ref86","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1023\/A:1007413511361","article-title":"On the optimality of the simple Bayesian classifier under zero-one loss","volume":"29","author":"Domingos","year":"1997","journal-title":"Mach. Learn."},{"key":"ref87","volume-title":"Pattern Recognition: Introduction Terminology","author":"Duin","year":"2016"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1136\/emj.20.5.453"},{"key":"ref89","first-page":"367","article-title":"Static versus dynamic sampling for data mining","volume-title":"Proc. 2nd Int. Conf. Knowl. Discov. Data Mining","author":"John"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_25"},{"key":"ref91","first-page":"397","article-title":"The learning-curve sampling method applied to model-based clustering","volume":"2","author":"Meek","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref92","first-page":"1319","article-title":"Approximating learning curves for active-learning-driven annotation","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Tomanek"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102414"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77002-2_8"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24465-5_26"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3251957"},{"key":"ref97","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"ref98","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0711-5","volume-title":"A Probabilistic Theory of Pattern Recognition","volume":"31","author":"Devroye","year":"1996"},{"key":"ref99","first-page":"3198","article-title":"Open problem: Monotonicity of learning","volume-title":"Proc. Conf. Learn. Theory","author":"Viering"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3406325.3451087"},{"key":"ref101","article-title":"Learning curve theory","author":"Hutter","year":"2021"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.15388\/Informatica.2014.19"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30134-9_71"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90045-7"},{"key":"ref105","first-page":"911","article-title":"Can neural networks do better than the vapnik-chervonenkis bounds?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cohn"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26419-1_1"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref110","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.478"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref113","volume-title":"Estimation of Dependences Based on Empirical Data Berlin","author":"Vapnik","year":"1982"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref115","first-page":"837","article-title":"A critique of the valiant model","volume-title":"Proc. 11th Int. Conf. Artif. Intell.","author":"Buntine"},{"key":"ref116","first-page":"89","article-title":"Average case analysis of empirical and explanation-based learning algorithms","author":"Sarrett","year":"1989"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-27366-2_9"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/bf00114010"},{"key":"ref119","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59119-2_184"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1505"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015592"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/34.879795"},{"key":"ref124","first-page":"413","article-title":"Rates of convergence for nearest neighbor procedures","volume-title":"Proc. Hawaii Int. Conf. Syst. Sci.","author":"Cover"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054408"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(93)90013-M"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.226960"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-213-7.50011-0"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.4.605"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.1.140"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.45.6056"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.3.374"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1989.118274"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-094829-4.50020-9"},{"key":"ref136","volume-title":"The Foundations of Statistics","author":"Savage","year":"1954"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1093\/bjps\/17.4.319"},{"key":"ref138","first-page":"226","article-title":"When ignorance is bliss","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Gr\u00fcnwald"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1086\/289490"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"issue":"1","key":"ref141","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1007601601278","article-title":"Upper and lower bounds on the learning curve for gaussian processes","volume":"40","author":"Williams","year":"2000","journal-title":"Mach. Learn."},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712990"},{"key":"ref143","article-title":"Posterior variance analysis of gaussian processes with application to average learning curves","author":"Lederer","year":"2019"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-014-5437-0"},{"key":"ref145","first-page":"302","article-title":"General bounds on bayes errors for regression with gaussian processes","volume-title":"Proc. 11th Int. Conf. Neural Inf. Process. Syst.","author":"Opper"},{"key":"ref146","first-page":"344","article-title":"Learning Curves for Gaussian Processes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sollich"},{"key":"ref147","article-title":"Design problems for optimal surface interpolation","author":"Michelli","year":"1979"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511600814"},{"key":"ref149","first-page":"218","article-title":"Finite-dimensional approximation of gaussian processes","volume-title":"Proc. 11th Int. Conf. Neural Inf. Process. Syst.","author":"Trecate"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_25"},{"key":"ref151","first-page":"17","article-title":"Regression with Gaussian processes: Average case performance","author":"Opper","year":"1997","journal-title":"Proc. Theor. Aspects Neural Comput.: A Multidisciplinary Perspective"},{"key":"ref152","first-page":"255","article-title":"Learning curves for gaussian processes regression: A framework for good approximations","volume-title":"Proc. 13th Int. Conf. Neural Inf. Process. Syst.","author":"Malzahn"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_39"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0064"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177004776"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1006\/jath.1996.0071"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1016\/S0096-3003(01)00298-3"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89689-0_76"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2013.808567"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5586-4"},{"key":"ref161","first-page":"1","article-title":"Generating well-behaved learning curves: An empirical study","volume-title":"Proc. Int. Conf. Data Sci.","author":"Weiss"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1037\/h0073117"},{"key":"ref163","first-page":"335","article-title":"Phase transitions in learning","volume":"18","author":"Vetter","year":"1997","journal-title":"J. Mind. Behav."},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/4\/4\/020"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.41.7097"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.65.499"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.48.4805"},{"key":"ref168","article-title":"Statistical Mechanics of Learning: Generalization","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"Opper","year":"1995"},{"key":"ref169","first-page":"523","article-title":"Statistical mechanics of learning in a large committee machine","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schwarze"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/20\/5\/015"},{"issue":"Part 2","key":"ref171","first-page":"763","article-title":"Learning to generalize","volume":"3","author":"Opper","year":"2001","journal-title":"Front. Life"},{"key":"ref172","first-page":"32","article-title":"Annealed theories of learning","volume-title":"Proc. CTP-PRSRI Joint Workshop Theor. Phys.","author":"Seung"},{"key":"ref173","first-page":"217","article-title":"Theoretical issues in learning from examples","volume-title":"Proc. NEC Res. Symp.","author":"Sompolinsky"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/24\/5\/017"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.75.016101"},{"key":"ref176","first-page":"2951","article-title":"Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Ipsen"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4206"},{"key":"ref178","article-title":"More data can hurt for linear regression: Sample-wise double descent","author":"Nakkiran","year":"2019"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2001875117"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49055-7_27"},{"key":"ref181","article-title":"The equivalence between row and column linear regression","author":"Tresp","year":"2002"},{"key":"ref182","article-title":"Optimal regularization can mitigate double descent","author":"Nakkiran","year":"2020"},{"key":"ref183","first-page":"1","article-title":"Small sample size generalization","volume-title":"Proc. Scand. Conf. Image Anal.","author":"Duin"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1007\/s100440050013"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.86.4410"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/ab4c8b"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.08.022"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1214\/21-aos2133"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3909"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34166-3_34"},{"key":"ref191","first-page":"1863","article-title":"Minimizing the misclassification error rate using a surrogate convex loss","volume-title":"Proc. 29th Int. Conf. Mach. Learn.","author":"Ben-david"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1142\/9789814656535_0003"},{"key":"ref193","first-page":"1173","article-title":"Large margin classifiers: Convex loss, low noise, and convergence rates","volume-title":"Proc. 16th Int. Conf. Neural Inf. Process. Syst.","author":"Bartlett"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89197-0_45"},{"key":"ref195","first-page":"839","article-title":"Less is more: Active learning with support vector machines","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Schohn"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.340"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899635"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2945942"},{"key":"ref201","first-page":"7478","article-title":"Minimizers of the empirical risk and risk monotonicity","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Loog"},{"key":"ref202","article-title":"Grokking: Generalization beyond overfitting on small algorithmic datasets","author":"Power","year":"2022"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0071"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/11559887_12"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1214\/17-BA1085"},{"key":"ref206","first-page":"813","article-title":"Bounds on individual risk for log-loss predictors","volume":"19","author":"Gr\u00fcnwald","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44584-3_42"},{"key":"ref208","article-title":"Risk-monotonicity in statistical learning","author":"Mhammedi","year":"2020"},{"key":"ref209","first-page":"842","article-title":"Monotone learning","volume-title":"Proc. 35th Annu. Workshop Comput. Learn. Theory","author":"Bousquet"},{"issue":"157","key":"ref210","first-page":"1","article-title":"A universally consistent learning rule with a universally monotone error","volume":"23","author":"Pestov","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref211","volume-title":"Construction and Assessment of Classification Rules","author":"Hand","year":"1997"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.3758\/BF03211315"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.3758\/BF03212979"},{"key":"ref214","article-title":"A note on high-probability versus in-expectation guarantees of generalization bounds in machine learning","author":"Mey","year":"2020"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1214\/07-STS249"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09944190.pdf?arnumber=9944190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:04:54Z","timestamp":1706756694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9944190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":211,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3220744","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}