Presentation 2014-07-17
α-divergence derived as the generalized rate function in Tsallis statistics
Hiroki Suyari, Antonio M. Scarfone,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The generalized binomial distribution in Tsallis statistics (power-law system) is explicitly formulated from the precise q-Stirling's formula. The α-divergence (or q-divergence) is uniquely derived from the generalized binomial distribution in the sense that when α → -1 (i.e., q → 1) it recovers KL divergence obtained from the standard binomial distribution. Based on these combinatorial considerations, it is shown that α-divergence (or q-divergence) is appeared as the generalized rate function in the large deviation estimate in Tsallis statistics.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) α-divergence / generalized rate function / generalized binomial distribution / large deviation estimate / power-law system
Paper # IT2014-16
Date of Issue

Conference Information
Committee IT
Conference Date 2014/7/10(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 Information Theory (IT)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) α-divergence derived as the generalized rate function in Tsallis statistics
Sub Title (in English)
Keyword(1) α-divergence
Keyword(2) generalized rate function
Keyword(3) generalized binomial distribution
Keyword(4) large deviation estimate
Keyword(5) power-law system
1st Author's Name Hiroki Suyari
1st Author's Affiliation Graduate School of Advanced Integration Science, Chiba University()
2nd Author's Name Antonio M. Scarfone
2nd Author's Affiliation Istituto dei Sistemi Complessi (ISC-CNR)
Date 2014-07-17
Paper # IT2014-16
Volume (vol) vol.114
Number (no) 138
Page pp.pp.-
#Pages 6
Date of Issue