Author： McAllester D.A.
Publisher： Springer Publishing Company
ISSN： 0885-6125
Source： Machine Learning, Vol.51, Iss.1, 2003-04, pp. : 5-21
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
PAC-Bayesian learning methods combine the informative priors of Bayesian methods with distribution-free PAC guarantees. Stochastic model selection predicts a class label by stochastically sampling a classifier according to a “posterior distribution” on classifiers. This paper gives a PAC-Bayesian performance guarantee for stochastic model selection that is superior to analogous guarantees for deterministic model selection. The guarantee is stated in terms of the training error of the stochastic classifier and the KL-divergence of the posterior from the prior. It is shown that the posterior optimizing the performance guarantee is a Gibbs distribution. Simpler posterior distributions are also derived that have nearly optimal performance guarantees.
Related content
Machine Learning, Vol. 37, Iss. 3, 1999-12 ,pp. :
Access to resources
Recommend
By Abdallh Ahmed Abou-Elyazied Dupré Luc
COMPEL: Int J for Computation and Maths. in Electrical and Electronic Eng., Vol. 33, Iss. 3, 2014-04 ,pp. :
Computer Speech & Language, Vol. 13, Iss. 2, 1999-04 ,pp. :