Presentation 2004/10/12
Stochastic Complexities in Learning of Normal Mixture Models by 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 approach, proposed as an approximation of the Baysian learning, has provided computational tractability and good generalization performance in many applications. In spite of these advantages, the properties and capabilities of the Variational Bayes learning itself have not been clarified yet. It is still unknown how good approximation the Variational Bayes approach can achieve. In this paper, we discuss the Variational Bayes learning of normal mixture models and derive the lower bounds of the stochastic complexities that show us the accuracy of Variational Bayes learning as an approximation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Normal Mixture Model / Variational Bayes Learning / Stochastic Complexity / Singular Statistical Model
Paper # NC2004-78
Date of Issue

Conference Information
Committee NC
Conference Date 2004/10/12(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 in Learning of Normal Mixture Models by Variational Bayes Approach
Sub Title (in English)
Keyword(1) Normal 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 2004/10/12
Paper # NC2004-78
Volume (vol) vol.104
Number (no) 349
Page pp.pp.-
#Pages 6
Date of Issue