PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

PAC-Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier
Alexandre Lacasse, François Laviolette, Mario Marchand, Pascal Germain and Nicolas Usunier
In: NIPS'06, 4-7 Dec 2006, Vancouver, Canada.

Abstract

We propose new PAC-Bayes bounds for the risk of the weighted majority vote that depend on the mean and variance of the error of its associated Gibbs classifier. We show that these bounds can be smaller than the risk of the Gibbs classifier and can be arbitrarily close to zero even if the risk of the Gibbs classifier is close to 1/2. Moreover, we show that these bounds can be uniformly estimated on the training data for all possible posteriors Q. Moreover, they can be improved by using a large sample of unlabelled data.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:2862
Deposited By:Nicolas Usunier
Deposited On:22 November 2006