Hessian structures and divergence functions on deformed exponential families

Hiroshi Matsuzoe

Masayuki Henmi

pp. 57-80

in: Frank Nielsen (ed), Geometric theory of information, Berlin, Springer, 2014

Abstract

A Hessian structure (( abla , h)) on a manifold is a pair of a flat affine connection ( abla ) and a semi-Riemannian metric (h) which is given by a Hessian of some function. In information geometry, it is known that an exponential family naturally has dualistic Hessian structures and their canonical divergences coincide with the Kullback-Leibler divergences, which are also called the relative entropies. A deformed exponential family is a generalization of exponential families. A deformed exponential family naturally has two kinds of dualistic Hessian structures and conformal structures of Hessian metrics. In this paper, geometry of such Hessian structures and conformal structures are summarized. In addition, divergence functions on these Hessian manifolds are constructed from the viewpoint of estimating functions. As an application of such Hessian structures to statistics, a generalization of independence and geometry of generalized maximum likelihood method are studied.