alpha-Divergence derived as the generalized rate function in Tsallis statistics

Autor:	H. Suyari and A.M. Scarfone
Jazyk:	angličtina
Rok vydání:	2014
Předmět:	generalized rate func tion power-law system alpha -divergence large deviation estimate generalized binomial distribution
Zdroj:	IEICE technical report The Institute of Electronics, Information and Communication Engineers 114 (2014): 25–30. info:cnr-pdr/source/autori:H. Suyari and A.M. Scarfone/titolo:alpha-Divergence derived as the generalized rate function in Tsallis statistics/doi:/rivista:IEICE technical report The Institute of Electronics, Information and Communication Engineers/anno:2014/pagina_da:25/pagina_a:30/intervallo_pagine:25–30/volume:114
Popis:	The generalized binomial distribution in Tsallis statistics (power-law system) is explicitly formulated from the precise q-Stirling's formula. The alpha-divergence (or q-divergence) is uniquely derived from the generalized binomial distribution in the sense that when q->-1 (i.e., q->1) it recovers KL divergence obtained from the standard binomial distribution. Based on these combinatorial considerations, it is shown that alpha-divergence (or q-divergence) is appeared as the generalized rate function in the large deviation estimate in Tsallis statistics.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=cnr_________::b88dfcbbe92ed4aacf75d6f74d839e48 https://publications.cnr.it/doc/311491 Zobrazit plný text záznamu