Workshop

Maximizing the Kullback-Leibler distance

• Johannes Rauh (Max Planck Institute for Mathematics in the Sciences, Germany)
University n.n. Universität Leipzig (Leipzig)

Abstract

Nihat Ay proposed the following problem [1], motivated from statistical learning theory: Let $\mathcal{E}$ be an exponential family. Find the maximizer of the Kullback-Leibler distance $D(P\|\mathcal{E})$ from $\mathcal{E}$. A maximizing probability measure $P$ has a lot of interesting properties. For example, the restriction of $\hat{P}$ to the support of $P$ will be equal to $P$, i.e. $\hat{P}(x) = P(x)\hat{P}(Z)$ if $x\in\ensuremath{\mathrm{supp}}(P)$ (for the proof in the most general case see [2]). This simple property can be used to transform the problem into another form. The first observation is that probability measures having this "projection property" always come in pairs $P_{1},P_{2}$, such that $P_{1}$ and $P_{2}$ have the same sufficient statistics $A$ and disjoint supports. Therefore we can solve the original problem by investigating the kernel of the sufficient statistics $\ker A$. If we find all local maximizers of \begin{equation*}\overline D(M) := \sum_{x} M(x) \log |M(x)|, \quad M\in\ker A,\end{equation*} subject to $\|M\|_{\ell_{1}} \le 2$, then we know all maximizers of the original problem. The talk will present the transformed problem and its relation to the original problem. In the end I will give some consequences for the solutions of the original problem.
[1] N. Ay: An Information-Geometric Approach to a Theory of Pragmatic Structuring. The Annals of Probability 30 (2002) 416-436.
[2] F. Matúš: Optimality conditions for maximizers of the information divergence from an exponential family. Kybernetika 43, 731-746.

conference
02.08.10 06.08.10

Information Geometry and its Applications III

Universität Leipzig University n.n.

Antje Vandenberg

Max-Planck-Institut für Mathematik in den Naturwissenschaften

Nihat Ay

Max Planck Institute for Mathematics in the Sciences, Germany

Paolo Gibilisco

Università degli Studi di Roma "Tor Vergata", Italy

František Matúš

Academy of Sciences of the Czech Republic, Czech Republic