Finding the Maximizers of the Information Divergence from an Exponential Family

preprint2009arXivOpen access

Abstract

This paper investigates maximizers of the information divergence from an exponential family EE. It is shown that the rIrI-projection of a maximizer PP to EE is a convex combination of PP and a probability measure P−P_- with disjoint support and the same value of the sufficient statistics AA. This observation can be used to transform the original problem of maximizing D(⋅∣∣E)D(\cdot||E) over the set of all probability measures into the maximization of a function $\Dbar$ over a convex subset of ker⁡A\ker A. The global maximizers of both problems correspond to each other. Furthermore, finding all local maximizers of $\Dbar$ yields all local maximizers of D(⋅∣∣E)D(\cdot||E). This paper also proposes two algorithms to find the maximizers of $\Dbar$ and applies them to two examples, where the maximizers of D(⋅∣∣E)D(\cdot||E) were not known before.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.