Repository | Book | Chapter
(2014) Geometric theory of information, Dordrecht, Springer.
Hessian structures and divergence functions on deformed exponential families
Hiroshi Matsuzoe, Masayuki Henmi
pp. 57-80
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.
Publication details
DOI: 10.1007/978-3-319-05317-2_3
Full citation:
Matsuzoe, H. , Henmi, M. (2014)., Hessian structures and divergence functions on deformed exponential families, in F. Nielsen (ed.), Geometric theory of information, Dordrecht, Springer, pp. 57-80.
This document is unfortunately not available for download at the moment.