Presentation 2005/3/23
Stochastic Complexities for Mixture of Exponential Family in Variational Bayes Approach
Kazuho WATANABE, Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Variational Bayes learning, proposed as an approximation of the Bayesian learning, has provided computational tractability and good generalization performance in many applications. However, little has been done to investigate its theoretical properties. In this paper, we discuss the Variational Bayes learning of the mixture of exponential families and derive the upper and lower bounds of the stochastic complexities or the marginal likelihoods. We show that the stochastic complexities become smaller than those of regular statistical models, which means the advantage of the Bayesian learning still remains in the Variational Bayes learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Mixture Model / Variational Bayes Learning / Stochastic Complexity / Singular Statistical Model
Paper # NC2004-211
Date of Issue

Conference Information
Committee NC
Conference Date 2005/3/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stochastic Complexities for Mixture of Exponential Family in Variational Bayes Approach
Sub Title (in English)
Keyword(1) Mixture Model
Keyword(2) Variational Bayes Learning
Keyword(3) Stochastic Complexity
Keyword(4) Singular Statistical Model
1st Author's Name Kazuho WATANABE
1st Author's Affiliation Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology()
2nd Author's Name Sumio WATANABE
2nd Author's Affiliation P&I Lab, Tokyo Institute of Technology
Date 2005/3/23
Paper # NC2004-211
Volume (vol) vol.104
Number (no) 760
Page pp.pp.-
#Pages 6
Date of Issue