A Note on the PAC Bayesian Theorem

Simple item page
dc.creatorMaurer, Andreas
dc.date2004-11-30
dc.date.accessioned2026-07-07T03:22:06Z
dc.date.available2026-07-07T03:22:06Z
dc.descriptionWe prove general exponential moment inequalities for averages of [0,1]-valued iid random variables and use them to tighten the PAC Bayesian Theorem. The logarithmic dependence on the sample count in the enumerator of the PAC Bayesian bound is halved.
dc.description9 pages
dc.identifierhttps://arxiv.org/abs/cs/0411099
dc.identifierhttp://arxiv.org/abs/cs/0411099
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32463
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectI.5.1
dc.titleA Note on the PAC Bayesian Theorem
dc.typetext

Files

Collections

arXiv