Presentation 2003/1/28
Extended Formula for Divergence Measures using Invariance
Masato UCHIDA, Hiroyuki SHIOYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The discriminant measure (information divergence) "f-divergence", which is used as a generalized phenotype of discriminant measures between two probability distributions, is defined by using a class of convex functions. In this paper, we derive a new class of discriminant measures defined on the set of all positive finite measures using the invariance of f-divergence. We mention some of its effectiveness concerning the extension of divergence measures by showing that the proposed class includes measures that facilitate statistical data processing and are suitable for the explicit formulation and analysis of the ensemble learning method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Invariance of f-divergence / α-divergence / Positive Finite Measure / Ensemble Learning
Paper # NC2002-133
Date of Issue

Conference Information
Committee NC
Conference Date 2003/1/28(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) Extended Formula for Divergence Measures using Invariance
Sub Title (in English)
Keyword(1) Invariance of f-divergence
Keyword(2) α-divergence
Keyword(3) Positive Finite Measure
Keyword(4) Ensemble Learning
1st Author's Name Masato UCHIDA
1st Author's Affiliation Nippon Telegraph and Telephone Corporation, NTT Service Integration Laboratories()
2nd Author's Name Hiroyuki SHIOYA
2nd Author's Affiliation Department of Computer Science and Systems Engineering, Muroran Institute of Technology
Date 2003/1/28
Paper # NC2002-133
Volume (vol) vol.102
Number (no) 628
Page pp.pp.-
#Pages 6
Date of Issue