Presentation 2005/10/11
Stochastic Complexity of Stochastic Context Free Grammer on Variational Bayesian method
Tikara HOSINO, Kazuho WATANABE, Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Variational Bayesian method is proposed for the approximation of Bayesian method. In spite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian Stochastic Context Free Grammer which includes the true one thus the model is non-identifiable. We derive their asymptotic stochastic complexity. It is shown that in some prior condition, the stochastic complexity is much smaller than identifiable models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stochastic Context Free Grammer / Non-identifiable models / Variational Bayesian method / Stochastic Complexity
Paper # NC2005-50
Date of Issue

Conference Information
Committee NC
Conference Date 2005/10/11(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stochastic Complexity of Stochastic Context Free Grammer on Variational Bayesian method
Sub Title (in English)
Keyword(1) Stochastic Context Free Grammer
Keyword(2) Non-identifiable models
Keyword(3) Variational Bayesian method
Keyword(4) Stochastic Complexity
1st Author's Name Tikara HOSINO
1st Author's Affiliation Computational Intelligence and System Science, Tokyo Inistitute of Technology:Nihon Unisys, Ltd.()
2nd Author's Name Kazuho WATANABE
2nd Author's Affiliation Computational Intelligence and System Science, Tokyo Inistitute of Technology
3rd Author's Name Sumio WATANABE
3rd Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology
Date 2005/10/11
Paper # NC2005-50
Volume (vol) vol.105
Number (no) 342
Page pp.pp.-
#Pages 6
Date of Issue