Work

Optimally approximating exponential families

Year: 2011
Type: preprint
Abstract: This article studies exponential families $\mathcal{E}$ on finite sets such that the information divergence $D(P\|\mathcal{E})$ of an arbitrary probability distribution from $\mathcal{E}$ is 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
Language: English
Open Access status: green
OpenAlex ID: W2127416462
Cites: 10
Cited by: 2
Related to: 20