An Extended Cencov-Campbell Characterization of Conditional Information Geometry

by   Guy Lebanon, et al.

We formulate and prove an axiomatic characterization of conditional information geometry, for both the normalized and the nonnormalized cases. This characterization extends the axiomatic derivation of the Fisher geometry by Cencov and Campbell to the cone of positive conditional models, and as a special case to the manifold of conditional distributions. Due to the close connection between the conditional I-divergence and the product Fisher information metric the characterization provides a new axiomatic interpretation of the primal problems underlying logistic regression and AdaBoost.


page 1

page 2

page 3

page 4


A Note on the Kullback-Leibler Divergence for the von Mises-Fisher distribution

We present a derivation of the Kullback Leibler (KL)-Divergence (also kn...

One-parameter generalised Fisher information

We introduce the generalised Fisher information or the one-parameter ext...

Fisher-Rao geometry of Dirichlet distributions

In this paper, we study the geometry induced by the Fisher-Rao metric on...

On Voronoi diagrams and dual Delaunay complexes on the information-geometric Cauchy manifolds

We study the Voronoi diagrams of a finite set of Cauchy distributions an...

Fisher Information of a Family of Generalized Normal Distributions

In this brief note we compute the Fisher information of a family of gene...

Online Classification with Complex Metrics

We present a framework and analysis of consistent binary classification ...

Information geometry for phylogenetic trees

We propose a new space to model phylogenetic trees. It is based on a bio...