\alpha-divergence derived as the generalized rate function in a power-law system

MaRDI QIDQ6251441zbMATH OpenFDO

Authors Hiroki Suyari, Antonio M. Scarfone

Publication date 11 May 2014

Mathematics Subject Classification ID

Large deviations (60F10)

Abstract: 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 $alphaightarrow-1$ (i.e., $qightarrow1$) 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.

This page was built for publication: $\alpha$-divergence derived as the generalized rate function in a power-law system

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6251441)