{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:51:37Z","timestamp":1775325097927,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFC0804003"],"award-info":[{"award-number":["2017YFC0804003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806091"],"award-info":[{"award-number":["61806091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012234","name":"Shenzhen Peacock Plan","doi-asserted-by":"crossref","award":["KQTD2016112514355531"],"award-info":[{"award-number":["KQTD2016112514355531"]}],"id":[{"id":"10.13039\/501100012234","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["ZDSYS201703031748284"],"award-info":[{"award-number":["ZDSYS201703031748284"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alexander von Humboldt Foundation for a Humboldt Research Fellowship"},{"name":"NSFC\/RGC Joint Research Scheme through RGC","award":["N_C CityU120\/14"],"award-info":[{"award-number":["N_C CityU120\/14"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11461161006"],"award-info":[{"award-number":["11461161006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["KL 2698\/2-1"],"award-info":[{"award-number":["KL 2698\/2-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["GRK1589\/2"],"award-info":[{"award-number":["GRK1589\/2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Federal Ministry of Science and Education","award":["031L0023A"],"award-info":[{"award-number":["031L0023A"]}]},{"name":"Federal Ministry of Science and Education","award":["01IS18051A"],"award-info":[{"award-number":["01IS18051A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/tit.2019.2893916","type":"journal-article","created":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T04:23:22Z","timestamp":1548131002000},"page":"2995-3021","source":"Crossref","is-referenced-by-count":28,"title":["Data-Dependent Generalization Bounds for Multi-Class Classification"],"prefix":"10.1109","volume":"65","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5383-467X","authenticated-orcid":false,"given":"Yunwen","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Urun","family":"Dogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0224-9216","authenticated-orcid":false,"given":"Ding-Xuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6829-3725","authenticated-orcid":false,"given":"Marius","family":"Kloft","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"315","article-title":"Generalization error bounds for learning to rank: Does the length of document lists matter?","author":"tewari","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","first-page":"148","article-title":"On the method of bounded differences","author":"mcdiarmid","year":"1989","journal-title":"Surveys in Combinatorics"},{"key":"ref71","author":"nocedal","year":"2006","journal-title":"Numerical Optimization"},{"key":"ref70","first-page":"427","article-title":"Revisiting Frank–Wolfe: Projection-free sparse convex optimization","author":"jaggi","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/132"},{"key":"ref77","first-page":"593","article-title":"Large-scale multi-label learning with missing labels","author":"yu","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref74","first-page":"2199","article-title":"Smoothness, low noise and fast rates","author":"srebro","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","first-page":"2760","article-title":"Learning kernels using local Rademacher complexity","author":"cortes","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s00440-013-0545-5","article-title":"Sequential complexities and uniform martingale laws of large numbers","volume":"161","author":"rakhlin","year":"2014","journal-title":"Probab Theory Rel Fields"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/18.971753"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5285-8"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2011.01.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000000098"},{"key":"ref32","article-title":"Multi-class support vector machines","author":"weston","year":"1998"},{"key":"ref31","first-page":"265","article-title":"On the algorithmic implementation of multiclass kernel-based vector machines","volume":"2","author":"crammer","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref30","first-page":"325","article-title":"Top-k multiclass SVM","author":"lapin","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","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"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/18.930926"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2008.04.001"},{"key":"ref34","first-page":"1097","article-title":"Rademacher complexity bounds for non-I.I.D. processes","author":"mohri","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","first-page":"527","article-title":"Covering number bounds of certain regularized linear function classes","volume":"2","author":"zhang","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.813564"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1006\/jcom.2002.0635"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.163"},{"key":"ref28","first-page":"2026","article-title":"Multi-class SVMs: From tighter data-dependent generalization bounds to novel algorithms","author":"lei","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref27","author":"varma","year":"2015","journal-title":"NIPS Workshop eXtreme Classification"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref66","first-page":"361","article-title":"RCV1: A new benchmark collection for text categorization research","volume":"5","author":"lewis","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref29","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref67","first-page":"41","article-title":"A comparison of event models for naive Bayes text classification","volume":"752","author":"mccallum","year":"1998","journal-title":"Proc AAAI Workshop Learn Text Categorization"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000042993.50813.60"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36169-3_29"},{"key":"ref1","volume":"1","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref20","first-page":"51","article-title":"Conditional probability tree estimation analysis and algorithms","author":"beygelzimer","year":"2009","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939756"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767701"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623651"},{"key":"ref23","first-page":"1","article-title":"Learning taxonomy adaptation in large-scale classification","volume":"17","author":"babbar","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974348.27"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0178161"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/03610920903140288"},{"key":"ref51","first-page":"2551","article-title":"VC theory of large margin multi-category classifiers","volume":"8","author":"guermeur","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref59","first-page":"1007","article-title":"On the consistency of multiclass classification methods","volume":"8","author":"tewari","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273499"},{"key":"ref56","first-page":"892","article-title":"Maximum margin multiclass nearest neighbors","author":"kontorovich","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2017.06.003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114804"},{"key":"ref53","first-page":"485","article-title":"Multiclass learning approaches: A theoretical comparison with implications","author":"daniely","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"2377","article-title":"Multiclass learnability and the ERM principle","volume":"16","author":"daniely","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/aos\/1015362182","article-title":"Empirical margin distributions and bounding the generalization error of combined classifiers","volume":"30","author":"koltchinskii","year":"2002","journal-title":"Ann Statist"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s100440200015"},{"key":"ref40","first-page":"46","article-title":"Multi-class classification with maximum margin multiple kernel","author":"cortes","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref13","author":"lecun","year":"1998","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref14","author":"asuncion","year":"2007","journal-title":"UCI Machine Learning Repository"},{"key":"ref15","author":"partalas","year":"2015","journal-title":"Lshtc A benchmark for large-scale text classification"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"ref16","author":"varma","year":"2013","journal-title":"NIPS Workshop eXtreme Classification"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"},{"key":"ref17","author":"varadarajan","year":"2015","journal-title":"Efficient Large Scale Video Classification"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/BF02384340"},{"key":"ref18","first-page":"730","article-title":"Sparse local embeddings for extreme multi-label classification","author":"bhatia","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","author":"de la pe\u00f1a","year":"2012","journal-title":"Decoupling From Dependence to Independence"},{"key":"ref19","first-page":"163","article-title":"Label embedding trees for large multi-class tasks","author":"bengio","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530517500026"},{"key":"ref4","first-page":"1","article-title":"A unified view on multi-class support vector classification","volume":"17","author":"do?an","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/72.991427"},{"key":"ref6","first-page":"219","article-title":"Part-of-speech tagging","author":"voutilainen","year":"2003","journal-title":"The Oxford Handbook of Computational Linguistics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.754617"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0417-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2008.07.001"},{"key":"ref9","author":"mohri","year":"2012","journal-title":"Foundations of Machine Learning"},{"key":"ref46","author":"steinwart","year":"2008","journal-title":"Support Vector Machines"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0042947"},{"key":"ref48","first-page":"1225","article-title":"Statistical analysis of some multi-category large margin classification methods","volume":"5","author":"zhang","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/1116025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1962.tb02419.x"},{"key":"ref41","first-page":"2501","article-title":"Multi-class deep boosting","author":"kuznetsov","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"2514","article-title":"Structured prediction theory based on factor graph complexity","author":"cortes","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_1"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/8694135\/08620322.pdf?arnumber=8620322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:16Z","timestamp":1657746556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8620322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":84,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tit.2019.2893916","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5]]}}}