Show simple item record

dc.contributor.authorHonorio Carrillo, Jean
dc.contributor.authorJaakkola, Tommi S.
dc.date.accessioned2018-01-10T16:52:14Z
dc.date.available2018-01-10T16:52:14Z
dc.date.issued2014-04
dc.identifier.issn1938-7228
dc.identifier.urihttp://hdl.handle.net/1721.1/113045
dc.description.abstractWe analyze the expected risk of linear classifiers for a fixed weight vector in the “minimax” setting. That is, we analyze the worst-case risk among all data distributions with a given mean and covariance. We provide a simpler proof of the tight polynomial-tail bound for general random variables. For sub-Gaussian random variables, we derive a novel tight exponential bound. We also provide new PAC-Bayes finite-sample guarantees when training data is available. Our “minimax” generalization bounds are dimensionality-independent and O(√1/m) for m samples.en_US
dc.language.isoen_US
dc.publisherJournal of Machine Learning Researchen_US
dc.relation.isversionofhttp://proceedings.mlr.press/v33/en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT Web Domainen_US
dc.titleTight bounds for the expected risk of linear classifiers and PAC-bayes finite-sample guaranteesen_US
dc.typeArticleen_US
dc.identifier.citationHonorio, Jean and Tomi Jaakkola. "Tight bounds for the expected risk of linear classifiers and PAC-bayes finite-sample guarantees." Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS), 22-25 April 2014, Reykjavik, Iceland, Journal of Machine Learning Research, 2014.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorHonorio Carrillo, Jean
dc.contributor.mitauthorJaakkola, Tommi S.
dc.relation.journalProceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS)en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsHonorio, Jean; Jaakkola, Tomien_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0003-0238-6384
dc.identifier.orcidhttps://orcid.org/0000-0002-2199-0379
dspace.mitauthor.errortrue
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record