论文信息 - A closed-form expression for the Sharma–Mittal entropy of exponential families

A closed-form expression for the Sharma–Mittal entropy of exponential families

The Sharma-Mittal entropies generalize the celebrated Shannon, R\'enyi and Tsallis entropies. We report a closed-form formula for the Sharma-Mittal entropies and relative entropies for arbitrary exponential family distributions. We instantiate explicitly the formula for the case of the multivariate Gaussian distributions and discuss on its estimation.

Frank Nielsen | Richard Nock | R. Nock | F. Nielsen

[1] C. R. Rao,et al. On the convexity of some divergence measures based on entropy functions , 1982, IEEE Trans. Inf. Theory.

[2] L. Cobb,et al. Estimation and Moment Recursion Relations for Multimodal Distributions of the Exponential Family , 1983 .

[3] L. Brown. Fundamentals of statistical exponential families: with applications in statistical decision theory , 1986 .

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

[5] Alfred O. Hero,et al. Applications of entropic spanning graphs , 2002, IEEE Signal Process. Mag..

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

[7] D. Brody. A note on exponential families of distributions , 2007, 0705.2173.

[8] L. Pronzato,et al. A class of Rényi information estimators for multidimensional densities , 2008, 0810.5302.

[9] O. Üzengi Aktürk,et al. Can Sobolev Inequality Be Written for Sharma-Mittal Entropy? , 2008 .

[10] G. Bagci,et al. Is Sharma-Mittal entropy really a step beyond Tsallis and Renyi entropies? , 2007, cond-mat/0703277.