Institute of Information Theory and Automation

You are here

Bibliography

Journal Article

On limiting towards the boundaries of exponential families

Matúš František

: Kybernetika vol.51, 5 (2015), p. 725-738

: GA13-20012S, GA ČR

: exponential family, variance function, Kullback--Leibler divergence, relative entropy, information divergence, mean parametrization, convex support

: 10.14736/kyb-2015-5-0725

: http://library.utia.cas.cz/separaty/2016/MTR/matus-0455604.pdf

(eng): This work studies the standard exponential families of probability measures on Euclidean spaces that have finite supports. In such a family parameterized by means, the mean is supposed to move along a segment inside the convex support towards an endpoint on the boundary of the support. Limit behavior of several quantities related to the exponential family is described explicitly. In particular, the variance functions and information divergences are studied around the boundary.

: BD

2019-01-07 08:39