PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Tighter PAC-Bayes bounds through distribution dependent priors
Guy Lever, Francois Laviolette and John Shawe-Taylor
Special Issue ALT 2010 2012.

Abstract

We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We use this framework to prove sharp risk bounds for stochastic exponential weights algorithms, and develop insights into controlling function class complexity in this method. In particular we consider controlling capacity with respect to the unknown geometry defined by the data-generating distribution. We also use the method to obtain new bounds for RKHS regularization schemes such as SVMs.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:9239
Deposited By:Guy Lever
Deposited On:21 February 2012