Presentation 2011-03-29
Minimum Variational Free Energy and Average Generalization Error in Latent Variable Models
Kazuho WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bayesian learning, widely used in many applied data-modeling problems, is often accomplished with approximation schemes because it requires intractable computation of the posterior distributions. In this study, we focus on the approximation method, variational Bayes, for latent variable models. The asymptotic form of the minimum of the variational free energy, the objective function of variational Bayes, is analyzed and related to the asymptotic theory of Bayesian learning. This analysis additionally implies a relationship between the generalization performance of the variational Bayes approach and the minimum variational free energy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) variational Bayes / variational free energy / generalization error / asymptotic analysis
Paper # IBISML2010-108
Date of Issue

Conference Information
Committee IBISML
Conference Date 2011/3/21(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Minimum Variational Free Energy and Average Generalization Error in Latent Variable Models
Sub Title (in English)
Keyword(1) variational Bayes
Keyword(2) variational free energy
Keyword(3) generalization error
Keyword(4) asymptotic analysis
1st Author's Name Kazuho WATANABE
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
Date 2011-03-29
Paper # IBISML2010-108
Volume (vol) vol.110
Number (no) 476
Page pp.pp.-
#Pages 8
Date of Issue