An Extended Cencov-Campbell Characterization of Conditional Information Geometry

07/11/2012
by   Guy Lebanon, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/25/2015

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...
07/22/2021

One-parameter generalised Fisher information

We introduce the generalised Fisher information or the one-parameter ext...
05/12/2020

Fisher-Rao geometry of Dirichlet distributions

In this paper, we study the geometry induced by the Fisher-Rao metric on...
06/12/2020

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...
11/17/2020

Fisher Information of a Family of Generalized Normal Distributions

In this brief note we compute the Fisher information of a family of gene...
10/23/2016

Online Classification with Complex Metrics

We present a framework and analysis of consistent binary classification ...
03/29/2020

Information geometry for phylogenetic trees

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