Preprint 73/2011

Optimally approximating exponential families

Johannes Rauh

Contact the author: Please use for correspondence this email.
Submission date: 28. Oct. 2011
published in: Kybernetika, 49 (2013) 2, p. 199-215 
MSC-Numbers: 62E17, 94A17, 60E05
Keywords and phrases: exponential family, information divergence, hierarchical models
Download full preprint: PDF (212 kB), PS ziped (321 kB)

This article studies exponential families Eon finite sets such that the information divergence D(PE) of an arbitrary probability distribution from Eis bounded by some constant D > 0. A particular class of low-dimensional exponential families that have low values of D can be obtained from partitions of the state space. The main results concern optimality properties of these partition exponential families. Exponential families where D = log(2) are studied in detail. This case is special, because if D < log(2), then Econtains all probability measures with full support.

16.03.2021, 02:14