Scaled Bregman divergences in a Tsallis scenario

Abstract

There exist two different versions of the Kullback-Leibler divergence (K-Ld) in Tsallis statistics, namely the usual generalized K-Ld and the generalized Bregman K-Ld. Problems have been encountered in trying to reconcile them. A condition for consistency between these two generalized K-Ld-forms by recourse to the additive duality of Tsallis statistics is derived. It is also shown that the usual generalized K-Ld subjected to this additive duality, known as the dual generalized K-Ld, is a scaled Bregman divergence. This leads to an interesting conclusion: the dual generalized mutual information is a scaled Bregman information. The utility and implications of these results are discussed.

18 pages. Iterative corrections

References in corpus (6)

• A possible deformed algebra and calculus inspired in nonextensive thermostatistics
• On Bregman Distances and Divergences of Probability Measures
• Generalized molecular chaos hypothesis and H-theorem: Problem of constraints and amendment of nonextensive statistical mechanics
• Specific heat and entropy of $N$-body nonextensive systems
• Generalized Statistics Variational Perturbation Approximation using q-Deformed Calculus
• The entropy in finite $N$-unit nonextensive systems: the ordinary average and $q$-average

Cited by in corpus (1)

• Deformed Statistics Kullback-Leibler Divergence Minimization within a Scaled Bregman Framework