Presentation 2004/10/12
Stochastic Complexity and Singularities in Hierarchical 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 etc. 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 and applied it to complete bipartite graph-type Bayesian networks. The models consist of two layers, one is observable and the other hidden. In this paper, extending the method to general hierarchical Bayesian networks, we clarify upper bounds of the asymptotic form of the stochastic complexities. We obtain a unified view of singularities in some models such as Bayesian networks, mixture models and hidden Markov models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bayesian network / Stochastic complexity / Algebraic geometry
Paper # NC2004-73
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 Complexity and Singularities in Hierarchical Bayesian Networks
Sub Title (in English)
Keyword(1) Bayesian network
Keyword(2) Stochastic complexity
Keyword(3) Algebraic geometry
1st Author's Name Keisuke YAMAZAKI
1st Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology()
2nd Author's Name Sumio WATANABE
2nd Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology
Date 2004/10/12
Paper # NC2004-73
Volume (vol) vol.104
Number (no) 349
Page pp.pp.-
#Pages 6
Date of Issue