dc.contributor.author | Honorio Carrillo, Jean | |
dc.contributor.author | Jaakkola, Tommi S. | |
dc.date.accessioned | 2018-01-10T16:52:14Z | |
dc.date.available | 2018-01-10T16:52:14Z | |
dc.date.issued | 2014-04 | |
dc.identifier.issn | 1938-7228 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/113045 | |
dc.description.abstract | We 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.iso | en_US | |
dc.publisher | Journal of Machine Learning Research | en_US |
dc.relation.isversionof | http://proceedings.mlr.press/v33/ | en_US |
dc.rights | Creative Commons Attribution-Noncommercial-Share Alike | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | en_US |
dc.source | MIT Web Domain | en_US |
dc.title | Tight bounds for the expected risk of linear classifiers and PAC-bayes finite-sample guarantees | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Honorio, 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.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.contributor.mitauthor | Honorio Carrillo, Jean | |
dc.contributor.mitauthor | Jaakkola, Tommi S. | |
dc.relation.journal | Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS) | en_US |
dc.eprint.version | Author's final manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dspace.orderedauthors | Honorio, Jean; Jaakkola, Tomi | en_US |
dspace.embargo.terms | N | en_US |
dc.identifier.orcid | https://orcid.org/0000-0003-0238-6384 | |
dc.identifier.orcid | https://orcid.org/0000-0002-2199-0379 | |
dspace.mitauthor.error | true | |
mit.license | OPEN_ACCESS_POLICY | en_US |