Presentation 2021-03-03
Learning coefficients of normal mixture models in one dimension.
Genki Watanabe, Ryuji Ito, Miki Aoyagi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Hierarchical learning models are widely used for data analysis in image or speech recognition, economics and so on. However, such models are singular and cannot be analyzed using the classic theories of regular statistical models. Therefore, it is necessary to construct mathematical analysis of singular models. Recently, Watanabe developed several theorems, for example, widely applicable information criterion, widely applicable Bayesian information criterion, and cross-validation based on mathematical theorems in algebraic geometry and algebraic analysis. In this paper, we consider the generalization error of the normal models in Bayesian estimation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Resolution of singularities / learning coefficients / singular models / normal mixture models
Paper # IBISML2020-48
Date of Issue 2021-02-23 (IBISML)

Conference Information
Committee IBISML
Conference Date 2021/3/2(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Organized and general sessions on machine learning
Chair Ichiro Takeuchi(Nagoya Inst. of Tech.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(AIST) / Koji Tsuda(NTT)
Assistant Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Miidas)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning coefficients of normal mixture models in one dimension.
Sub Title (in English)
Keyword(1) Resolution of singularities
Keyword(2) learning coefficients
Keyword(3) singular models
Keyword(4) normal mixture models
1st Author's Name Genki Watanabe
1st Author's Affiliation Nihon University(Nihon Univ.)
2nd Author's Name Ryuji Ito
2nd Author's Affiliation Nihon University(Nihon Univ.)
3rd Author's Name Miki Aoyagi
3rd Author's Affiliation Nihon University(Nihon Univ.)
Date 2021-03-03
Paper # IBISML2020-48
Volume (vol) vol.120
Number (no) IBISML-395
Page pp.pp.40-46(IBISML),
#Pages 7
Date of Issue 2021-02-23 (IBISML)