Chernoff information of exponential families

02/14/2011
by   Frank Nielsen, et al.
0

Chernoff information upper bounds the probability of error of the optimal Bayesian decision rule for 2-class classification problems. However, it turns out that in practice the Chernoff bound is hard to calculate or even approximate. In statistics, many usual distributions, such as Gaussians, Poissons or frequency histograms called multinomials, can be handled in the unified framework of exponential families. In this note, we prove that the Chernoff information for members of the same exponential family can be either derived analytically in closed form, or efficiently approximated using a simple geodesic bisection optimization technique based on an exact geometric characterization of the "Chernoff point" on the underlying statistical manifold.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/19/2020

Applications of Structural Statistics: Geometrical Inference in Exponential Families

Exponential families comprise a broad class of statistical models and pa...
research
07/08/2022

Revisiting Chernoff Information with Likelihood Ratio Exponential Families

The Chernoff information between two probability measures is a statistic...
research
05/06/2018

Statistical Inference and Exact Saddle Point Approximations

Statistical inference may follow a frequentist approach or it may follow...
research
03/30/2020

A note on Onicescu's informational energy and correlation coefficient in exponential families

The informational energy of Onicescu is a positive quantity that measure...
research
01/20/2014

Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means

Bayesian classification labels observations based on given prior informa...
research
12/31/2020

Likelihood Ratio Exponential Families

The exponential family is well known in machine learning and statistical...
research
11/16/2012

Objective Improvement in Information-Geometric Optimization

Information-Geometric Optimization (IGO) is a unified framework of stoch...

Please sign up or login with your details

Forgot password? Click here to reset