{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:19:05Z","timestamp":1761581945747,"version":"3.37.3"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jsait.2020.2981864","type":"journal-article","created":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T19:55:56Z","timestamp":1585252556000},"page":"106-120","source":"Crossref","is-referenced-by-count":3,"title":["Sample Compression, Support Vectors, and Generalization in Deep Learning"],"prefix":"10.1109","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7217-2934","authenticated-orcid":false,"given":"Christopher","family":"Snyder","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3112-4885","authenticated-orcid":false,"given":"Sriram","family":"Vishwanath","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2013","author":"mcallester","journal-title":"A PAC-Bayesian tutorial with a dropout bound","key":"ref10"},{"key":"ref11","first-page":"809","article-title":"(Not) bounding the true error","author":"langford","year":"2002","journal-title":"Advances in Neural Information Processing Systems 14"},{"key":"ref12","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"dziugaite","year":"2017","journal-title":"Proc Conf Uncertainty in Artif Intell (UAI)"},{"key":"ref13","first-page":"5947","article-title":"Exploring generalization in deep learning","author":"neyshabur","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst (NIPS)"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1162\/neco.1997.9.1.1"},{"year":"2017","author":"kawaguchi","journal-title":"Generalization in deep learning","key":"ref15"},{"key":"ref16","article-title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","author":"neyshabur","year":"2014","journal-title":"CoRR"},{"year":"2018","author":"arora","journal-title":"Stronger generalization bounds for deep nets via a compression approach","key":"ref17"},{"year":"2018","author":"zhou","journal-title":"Non-vacuous generalization bounds at the ImageNet scale A PAC-Bayesian compression approach","key":"ref18"},{"year":"1986","author":"littlestone","article-title":"Relating data compression and learnability","key":"ref19"},{"key":"ref4","first-page":"297","article-title":"Size-independent sample complexity of neural networks","author":"golowich","year":"2018","journal-title":"Proc 31st Conf on Learning Theory 75"},{"key":"ref3","article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","author":"neyshabur","year":"2018","journal-title":"CoRR"},{"key":"ref6","first-page":"6241","article-title":"Spectrally-normalized margin bounds for neural networks","author":"bartlett","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst (NIPS)"},{"key":"ref5","first-page":"1376","article-title":"Norm-based capacity control in neural networks","volume":"40","author":"neyshabur","year":"2015","journal-title":"Proc Conf Learning Theory (COLT)"},{"year":"2017","author":"neyshabur","journal-title":"A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TSP.2017.2708039"},{"year":"2018","author":"novak","journal-title":"Sensitivity and Generalization in Neural Networks an Empirical Study","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1023\/A:1007618624809"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/BF02478259"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/BF00993593"},{"key":"ref22","first-page":"1461","article-title":"PAC-Bayes risk bounds for stochastic averages and majority votes of sample-compressed classifiers","volume":"8","author":"laviolette","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"297","article-title":"A PAC-Bayes sample compression approach to kernel methods","author":"germain","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref24","article-title":"Opening the black box of deep neural networks via information","author":"shwartz-ziv","year":"2017","journal-title":"CoRR"},{"year":"2018","author":"soudry","journal-title":"The implicit bias of gradient descent on separable data","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/3-540-44581-1_27"},{"year":"2016","author":"soudry","journal-title":"No bad local minima Data independent training error guarantees for multilayer neural networks","key":"ref25"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/8768428\/9047916-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/8768428\/09047916.pdf?arnumber=9047916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:17:32Z","timestamp":1651065452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9047916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2020.2981864","relation":{},"ISSN":["2641-8770"],"issn-type":[{"type":"electronic","value":"2641-8770"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}