Title :
α-divergence derived as the generalized rate function in a power-law system
Author :
Suyari, Hiroki ; Scarfone, Antonio Maria
Author_Institution :
Grad. Sch. of Adv. Integration Sci., Chiba Univ., Chiba, Japan
Abstract :
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 a 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.
Keywords :
binomial distribution; statistics; α-divergence; KL divergence; Tsallis statistics; generalized binomial distribution; generalized rate function; power-law system; q-Stirling formula; q-divergence; Australia; Entropy; Information theory; Random variables; Standards; Upper bound;
Conference_Titel :
Information Theory and its Applications (ISITA), 2014 International Symposium on
Conference_Location :
Melbourne, VIC