Entropy under disintegrations

02/18/2021
by   Juan Pablo Vigneaux, et al.
0

We consider the differential entropy of probability measures absolutely continuous with respect to a given σ-finite reference measure on an arbitrary measurable space. We state the asymptotic equipartition property in this general case; the result is part of the folklore but our presentation is to some extent novel. Then we study a general framework under which such entropies satisfy a chain rule: disintegrations of measures. We give an asymptotic interpretation for conditional entropies in this case. Finally, we apply our result to Haar measures in canonical relation.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/12/2018

Divergence measures estimation and its asymptotic normality theory : Discrete case

In this paper we provide the asymptotic theory of the general phi-diverg...
07/15/2019

On the Polarization of Rényi Entropy

Existing polarization theories have mostly been concerned with Shannon's...
04/16/2018

SpatEntropy: Spatial Entropy Measures in R

This article illustrates how to measure the heterogeneity of spatial dat...
07/14/2018

Piecewise Deterministic Markov Processes and their invariant measure

Piecewise Deterministic Markov Processes (PDMPs) are studied in a genera...
06/27/2012

A Split-Merge Framework for Comparing Clusterings

Clustering evaluation measures are frequently used to evaluate the perfo...
12/03/2019

On the Herbrand Functional Interpretation

We show that the types of the witnesses in the Herbrand functional inter...
12/14/2017

Rate of Change Analysis for Interestingness Measures

The use of Association Rule Mining techniques in diverse contexts and do...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.