A Note on the PAC Bayesian Theorem

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We 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.
9 pages

Keywords

Machine Learning, Artificial Intelligence, I.5.1

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/32463

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0411099
 http://arxiv.org/abs/cs/0411099

Collections

arXiv