Deformed statistics Kullback-Leibler divergence minimization within a scaled Bregman framework

DOI10.1016/J.PHYSLETA.2011.09.021MaRDI QIDQ1928038zbMATH OpenOpenAlexFDO

Authors R. C. Venkatesan, A. Plastino

Publication date 2 January 2013

Published in Physics Letters. A (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1102.1025

zbMATH Keywords

additive dualitydual generalized Kullback-Leibler divergencegeneralized Tsallis statisticsPythagorean theoremscaled Bregman divergences

Mathematics Subject Classification ID

Classical equilibrium statistical mechanics (general) (82B05) Statistical thermodynamics (82B30) Measures of information, entropy (94A17)

Abstract: The generalized Kullback-Leibler divergence (K-Ld) in Tsallis statistics [constrained by the additive duality of generalized statistics (dual generalized K-Ld)] is here reconciled with the theory of Bregman divergences for expectations defined by normal averages, within a measure-theoretic framework. Specifically, it is demonstrated that the dual generalized K-Ld is a scaled Bregman divergence. The Pythagorean theorem is derived from the minimum discrimination information-principle using the dual generalized K-Ld as the measure of uncertainty, with constraints defined by normal averages. The minimization of the dual generalized K-Ld, with normal averages constraints, is shown to exhibit distinctly unique features.

Recommendations

• Generalization of the Kullback-Leibler divergence in the Tsallis statistics
• Duality of maximum entropy and minimum divergence
• scientific article; zbMATH DE number 3896069
• Geometry of distributions associated with Tsallis statistics and properties of relative entropy minimization
• A generalization of the Kullback-Leibler divergence and its properties

Cites work

• 10.1162/153244303322753689
• A generalized maximum entropy approach to Bregman co-clustering and matrix approximation
• A Note on Minimum Discrimination Information
• Clustering with Bregman divergences.
• Comments on and correction to "Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy" (Jan 80 26-37) [Corresp.]
• Equivalence of the four versions of Tsallis's statistics
• scientific article; zbMATH DE number 3119624 (Why is no real title available?)
• scientific article; zbMATH DE number 3170754 (Why is no real title available?)
• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 3241743 (Why is no real title available?)
• I-divergence geometry of probability distributions and minimization problems
• Information gain within nonextensive thermostatistics
• Information geometry and Plefka's mean-field theory
• Information Theory and Statistics: A Tutorial
• Introduction to Nonextensive Statistical Mechanics
• Nonextensive information theoretic kernels on measures
• ON THE PROBLEM OF CONSTRAINTS IN NONEXTENSIVE FORMALISM: A QUANTUM MECHANICAL TREATMENT
• Properties of cross-entropy minimization
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Tsallis' entropy maximization procedure revisited
• Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems

Cited in

(4)

• Non-extensive entropy econometrics: new statistical features of constant elasticity of substitution-related models
• Generalized log-likelihood functions and Bregman divergences
• Interpreting Kullback--Leibler divergence with the Neyman-Pearson Lemma
• Generalization of the Kullback-Leibler divergence in the Tsallis statistics

This page was built for publication: Deformed statistics Kullback-Leibler divergence minimization within a scaled Bregman framework

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1928038)