A new class of entropic information measures, formal group theory and information geometry

In this work, we study generalized entropies and information geometry in a group-theoretical framework. We explore the conditions that ensure the existence of some natural properties and at the same time of a group-theoretical structure for a large class of entropies. In addition, a method for defining new entropies, using previously known ones with some desired group-theoretical properties is proposed. In the second part of this work, the information geometrical counterpart of the previous construction is examined and a general class of divergences are proposed and studied. Finally, a method of constructing new divergences from known ones is discussed; in particular, some results concerning the Riemannian structure associated with the class of divergences under investigation are formulated.

[1]  Shun-ichi Amari,et al.  Geometry of q-Exponential Family of Probability Distributions , 2011, Entropy.

[2]  Leandro Pardo,et al.  Asymptotic distribution of (h, φ)-entropies , 1993 .

[3]  P. Tempesta.  Formal groups and Z-entropies , 2015, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[4]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[5]  C. Tsallis.  Possible generalization of Boltzmann-Gibbs statistics , 1988 .

[6]  A. Plastino,et al.  Generalized thermostatistics based on the Sharma-Mittal entropy and escort mean values , 2002 .

[7]  P. Tempesta.  Beyond the Shannon-Khinchin Formulation: The Composability Axiom and the Universal Group Entropy , 2014, 1407.3807.

[8]  Shun-ichi Amari,et al.  Methods of information geometry , 2000 .

[9]  Frank Nielsen,et al.  A closed-form expression for the Sharma–Mittal entropy of exponential families , 2011, ArXiv.

[10]  P. Jizba,et al.  The world according to R enyi: thermodynamics of multifractal systems , 2002, cond-mat/0207707.

[11]  L. Bregman.  The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming , 1967 .

[12]  S. Zozor,et al.  General entropy-like uncertainty relations in finite dimensions , 2013, 1311.5602.

[13]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[14]  F. Opitz.  Information geometry and its applications , 2012, 2012 9th European Radar Conference.

[15]  Shun-ichi Amari,et al.  Geometry of deformed exponential families: Invariant, dually-flat and conformal geometries , 2012 .

[16]  Aleksandr Yakovlevich Khinchin,et al.  Mathematical foundations of information theory , 1959 .

[17]  M. Masi.  A step beyond Tsallis and Rényi entropies , 2005, cond-mat/0505107.

[18]  C. Tsallis.  Introduction to Nonextensive Statistical Mechanics: Approaching a Complex World , 2009 .

[19]  Piergiulio Tempesta,et al.  Uniqueness and characterization theorems for generalized entropies , 2017, ArXiv.

[20]  Piergiulio Tempesta,et al.  Group entropies, correlation laws, and zeta functions. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  J. Naudts.  Estimators, escort probabilities, and phi-exponential families in statistical physics , 2004, math-ph/0402005.

[22]  Andreas Daffertshofer,et al.  Exact time-dependent solutions of the Renyi Fokker–Planck equation and the Fokker–Planck equations related to the entropies proposed by Sharma and Mittal , 2000 .

[23]  G. Crooks.  On Measures of Entropy and Information , 2015 .

[24]  Ernesto P. Borges,et al.  Fisher metric from relative entropy group , 2018, 1805.11157.