Presentation 2005/3/23
Generalization Error of Variational Bayes Approach in Reduced Rank Regression
Shinichi NAKAJIMA, Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We prove that the variational Bayes approach in three-layer linear neural networks or reduced-rank regression models is asymptotically equivalent to a Stein type truncated estimation, and then theoretically clarify its generalization error.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) variational Bayes / reduced-rank / neural networks / Stein / shrinkage / unidentifiable model
Paper # NC2004-213
Date of Issue

Conference Information
Committee NC
Conference Date 2005/3/23(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) Generalization Error of Variational Bayes Approach in Reduced Rank Regression
Sub Title (in English)
Keyword(1) variational Bayes
Keyword(2) reduced-rank
Keyword(3) neural networks
Keyword(4) Stein
Keyword(5) shrinkage
Keyword(6) unidentifiable model
1st Author's Name Shinichi NAKAJIMA
1st Author's Affiliation Tokyo Institute of Technology:Nikon Corporation()
2nd Author's Name Sumio WATANABE
2nd Author's Affiliation Tokyo Institute of Technology
Date 2005/3/23
Paper # NC2004-213
Volume (vol) vol.104
Number (no) 760
Page pp.pp.-
#Pages 6
Date of Issue