Presentation 2003/7/21
Algebraic Geometry of Stochastic Complexity for Bayesian Networks
Keisuke YAMAZAKI, Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bayesian networks are now used in enormous fields, for example, system diagnosis, data mining, clusterings ets. In spite of wide range of their applications, the statistical properties have not yet been clarified because the models are nonidentifiable and non-regular. In recent years, however, we have developed a method to analyze non-regular models by using algebraic geometry. In this paper, applying this method to Bayesian networks with latent variables, we clarify the orders of the stochastic complexities. Our result shows that their upper bound is smaller than the dimension of the parameter space. This means that the Bayesian generalization error is also far smaller than that of a regular model, and that Schwarz's model selection criterion BIC needs to be improved for Bayesian networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bayesian Network / Stochastic Complesity / Algebraic Geometry
Paper # NC2003-28
Date of Issue

Conference Information
Committee NC
Conference Date 2003/7/21(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 Neurocomputing (NC)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Algebraic Geometry of Stochastic Complexity for Bayesian Networks
Sub Title (in English)
Keyword(1) Bayesian Network
Keyword(2) Stochastic Complesity
Keyword(3) Algebraic Geometry
1st Author's Name Keisuke YAMAZAKI
1st Author's Affiliation Tokyo Institute of Technology()
2nd Author's Name Sumio WATANABE
2nd Author's Affiliation Tokyo Institute of Technology
Date 2003/7/21
Paper # NC2003-28
Volume (vol) vol.103
Number (no) 227
Page pp.pp.-
#Pages 6
Date of Issue