{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:52:05Z","timestamp":1784299925608,"version":"3.55.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-2009030"],"award-info":[{"award-number":["CCF-2009030"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004052","name":"King Abdullah University of Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004052","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NSF through CAREER Award","award":["CCF-2239151"],"award-info":[{"award-number":["CCF-2239151"]}]},{"name":"NSF through CAREER Award","award":["IIS-2212182"],"award-info":[{"award-number":["IIS-2212182"]}]},{"name":"Adobe Data Science Research Award"},{"name":"Amazon Research Award"},{"DOI":"10.13039\/100006785","name":"Google Research Collabs Award","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tit.2023.3320098","type":"journal-article","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T17:42:13Z","timestamp":1695922933000},"page":"7909-7952","source":"Crossref","is-referenced-by-count":7,"title":["Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4501-5102","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Statistics and Applied Probability, University of California at Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidya","family":"Muthukumar","sequence":"additional","affiliation":[{"name":"Simons Institute for the Theory of Computing, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christos","family":"Thrampoulidis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1145\/3446776","article-title":"Understanding deep learning requires rethinking generalization","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Zhang"},{"issue":"48","key":"ref2","doi-asserted-by":"crossref","first-page":"30063","DOI":"10.1073\/pnas.1907378117","article-title":"Benign overfitting in linear regression","volume":"117","author":"Bartlett","year":"2020","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/20M1336072"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/21-AOS2133"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2984716"},{"issue":"169","key":"ref6","first-page":"1","article-title":"The optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization","volume":"21","author":"Kobak","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref7","first-page":"10104","article-title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","volume":"22","author":"Muthukumar","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref8","first-page":"5721","article-title":"Finite-sample analysis of interpolating linear classifiers in the overparameterized regime","volume":"22","author":"Chatterji","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/21M1415121"},{"key":"ref10","first-page":"8407","article-title":"Risk bounds for over-parameterized maximum margin classification on sub-Gaussian mixtures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1024691352"},{"key":"ref12","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref13","first-page":"2822","article-title":"The implicit bias of gradient descent on separable data","volume":"19","author":"Soudry","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","first-page":"1772","article-title":"The implicit bias of gradient descent on nonseparable data","volume-title":"Proc. 32nd Conf. Learn. Theory","volume":"99","author":"Ji"},{"key":"ref15","first-page":"91","article-title":"On the proliferation of support vectors in high dimensions","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","volume":"130","author":"Hsu"},{"key":"ref16","article-title":"Everything old is new again: A fresh look at historical approaches in machine learning","author":"Rifkin","year":"2002"},{"key":"ref17","first-page":"101","article-title":"In defense of one-vs-all classification","volume":"5","author":"Rifkin","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","article-title":"Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks","author":"Hui","year":"2020","journal-title":"arXiv:2006.07322"},{"key":"ref19","article-title":"Explicit regularization and implicit bias in deep network classifiers trained with the square loss","author":"Poggio","year":"2020","journal-title":"arXiv:2101.00072"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"issue":"40","key":"ref21","doi-asserted-by":"crossref","first-page":"24652","DOI":"10.1073\/pnas.2015509117","article-title":"Prevalence of neural collapse during the terminal phase of deep learning training","volume":"117","author":"Papyan","year":"2020","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref22","article-title":"Multi-class support vector machines","author":"Weston","year":"1998"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5197-3_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.105"},{"key":"ref25","first-page":"265","article-title":"On the algorithmic implementation of multiclass kernel-based vector machines","volume":"2","author":"Crammer","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000000098"},{"key":"ref27","first-page":"721","article-title":"Round Robin classification","volume":"2","author":"F\u00fcrnkranz","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"113","article-title":"Reducing multiclass to binary: A unifying approach for margin classifiers","volume":"1","author":"Allwein","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","article-title":"Squared Earth Mover\u2019s distance-based loss for training deep neural networks","author":"Hou","year":"2016","journal-title":"arXiv:1611.05916"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_15"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00125"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.neucom.2020.02.113","article-title":"Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions","volume":"400","author":"Bosman","year":"2020","journal-title":"Neurocomputing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CISS48834.2020.1570627167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11503415_10"},{"key":"ref37","first-page":"1391","article-title":"Cost-sensitive multiclass classification risk bounds","volume-title":"Proc. 30th Int. Conf. Int. Conf. Mach. Learn.","volume":"28","author":"Pires"},{"key":"ref38","article-title":"Multiclass classification calibration functions","author":"Pires","year":"2016","journal-title":"arXiv:1609.06385"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1015362183"},{"key":"ref40","first-page":"1","article-title":"Structured prediction theory based on factor graph complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Cortes"},{"key":"ref41","first-page":"1","article-title":"Multi-class SVMs: From tighter data-dependent generalization bounds to novel algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Lei"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2893916"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1134\/S105466181604009X"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3075137"},{"issue":"32","key":"ref46","doi-asserted-by":"crossref","first-page":"15849","DOI":"10.1073\/pnas.1903070116","article-title":"Reconciling modern machine-learning practice and the classical bias\u2013variance trade-off","volume":"116","author":"Belkin","year":"2019","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab633c"},{"issue":"45","key":"ref48","first-page":"1472","article-title":"Asymptotic behavior of support vector machine for spiked population model","volume":"18","author":"Huang","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1810420116"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683376"},{"key":"ref51","first-page":"1","article-title":"The impact of regularization on high-dimensional logistic regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Salehi"},{"key":"ref52","first-page":"3739","article-title":"Sharp asymptotics and optimal performance for inference in binary models","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Taheri"},{"key":"ref53","first-page":"2773","article-title":"Fundamental limits of ridge-regularized empirical risk minimization in high dimensions","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","volume":"130","author":"Taheri"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaab002"},{"key":"ref55","article-title":"The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime","author":"Montanari","year":"2019","journal-title":"arXiv:1911.01544"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3051849"},{"key":"ref57","article-title":"A precise high-dimensional asymptotic theory for boosting and min-\u21131-norm interpolated classifiers","author":"Liang","year":"2020","journal-title":"arXiv:2002.01586"},{"key":"ref58","first-page":"8417","article-title":"The performance analysis of generalized margin maximizers on separable data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Salehi"},{"key":"ref59","first-page":"12199","article-title":"Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Aubin"},{"key":"ref60","article-title":"Regularization in high-dimensional regression and classification via random matrix theory","author":"Lolas","year":"2020","journal-title":"arXiv:2003.13723"},{"key":"ref61","article-title":"A precise performance analysis of learning with random features","author":"Dhifallah","year":"2020","journal-title":"arXiv:2008.11904"},{"key":"ref62","article-title":"Interpolating classifiers make few mistakes","author":"Liang","year":"2021","journal-title":"arXiv:2101.11815"},{"key":"ref63","first-page":"8907","article-title":"Theoretical insights into multiclass classification: A high-dimensional asymptotic view","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Thrampoulidis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414099"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.82.2975"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/34\/21\/301"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11001"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-005-0462-7"},{"key":"ref70","first-page":"297","article-title":"A PAC-Bayes sample compression approach to kernel methods","volume-title":"Proc. ICML","author":"Germain"},{"key":"ref71","volume-title":"Introduction to Algorithms","author":"Cormen","year":"2009"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1080\/10556789408805554"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.neucom.2018.11.099","article-title":"Cost-sensitive support vector machines","volume":"343","author":"Iranmehr","year":"2019","journal-title":"Neurocomputing"},{"key":"ref74","first-page":"29820","article-title":"A geometric analysis of neural collapse with unconstrained features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhu"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s43670-022-00027-5"},{"key":"ref76","article-title":"Neural collapse under MSE loss: Proximity to and dynamics on the central path","author":"Han","year":"2021","journal-title":"arXiv:2106.02073"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.011"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2103091118"},{"key":"ref79","first-page":"3821","article-title":"Dissecting supervised constrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graf"},{"key":"ref80","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.860430"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.864420"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1974.1055219"},{"key":"ref84","article-title":"Benign overfitting in ridge regression","author":"Tsigler","year":"2020","journal-title":"arXiv:2009.14286"},{"key":"ref85","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017","journal-title":"arXiv:1703.11008"},{"key":"ref86","first-page":"23479","article-title":"Generalization for multiclass classification with overparameterized linear models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Subramanian"},{"key":"ref87","article-title":"Precise asymptotic generalization for multiclass classification with overparameterized linear models","author":"Wu","year":"2023","journal-title":"arXiv:2306.13255"},{"key":"ref88","first-page":"4907","article-title":"Support vector machines and linear regression coincide with very high-dimensional features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ardeshir"},{"key":"ref89","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref90","first-page":"1","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Menon"},{"key":"ref91","first-page":"18970","article-title":"Label-imbalanced and group-sensitive classification under overparameterization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kini"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1515\/9781400833344"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1214\/ECP.v18-2865"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10328924\/10266749-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10328924\/10266749.pdf?arnumber=10266749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T07:19:20Z","timestamp":1709363960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10266749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":95,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tit.2023.3320098","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}