Improved Vapnik Cervonenkis bounds

Simple item page
dc.creatorCatoni, Olivier
dc.date2004-10-11
dc.date.accessioned2026-07-07T08:06:33Z
dc.date.available2026-07-07T08:06:33Z
dc.descriptionWe give a new proof of VC bounds where we avoid the use of symmetrization and use a shadow sample of arbitrary size. We also improve on the variance term. This results in better constants, as shown on numerical examples. Moreover our bounds still hold for non identically distributed independent random variables. Keywords: Statistical learning theory, PAC-Bayesian theorems, VC dimension.
dc.identifierhttps://arxiv.org/abs/math/0410280
dc.identifierhttp://arxiv.org/abs/math/0410280
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/130644
dc.subjectStatistics Theory
dc.subjectProbability
dc.subject62H30, 68T05, 62B10
dc.titleImproved Vapnik Cervonenkis bounds
dc.typetext

Files

Collections

arXiv