On the Properties and Estimation of Pointwise Mutual Information Profiles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Czyż, Paweł, Grabowski, Frederic, Vogt, Julia E., Beerenwinkel, Niko, Marx, Alexander
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917677624197120
author Czyż, Paweł
Grabowski, Frederic
Vogt, Julia E.
Beerenwinkel, Niko
Marx, Alexander
author_facet Czyż, Paweł
Grabowski, Frederic
Vogt, Julia E.
Beerenwinkel, Niko
Marx, Alexander
contents The pointwise mutual information profile, or simply profile, is the distribution of pointwise mutual information for a given pair of random variables. One of its important properties is that its expected value is precisely the mutual information between these random variables. In this paper, we analytically describe the profiles of multivariate normal distributions and introduce a novel family of distributions, Bend and Mix Models, for which the profile can be accurately estimated using Monte Carlo methods. We then show how Bend and Mix Models can be used to study the limitations of existing mutual information estimators, investigate the behavior of neural critics used in variational estimators, and understand the effect of experimental outliers on mutual information estimation. Finally, we show how Bend and Mix Models can be used to obtain model-based Bayesian estimates of mutual information, suitable for problems with available domain expertise in which uncertainty quantification is necessary.
format Preprint
id arxiv_https___arxiv_org_abs_2310_10240
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Properties and Estimation of Pointwise Mutual Information Profiles
Czyż, Paweł
Grabowski, Frederic
Vogt, Julia E.
Beerenwinkel, Niko
Marx, Alexander
Machine Learning
Information Theory
The pointwise mutual information profile, or simply profile, is the distribution of pointwise mutual information for a given pair of random variables. One of its important properties is that its expected value is precisely the mutual information between these random variables. In this paper, we analytically describe the profiles of multivariate normal distributions and introduce a novel family of distributions, Bend and Mix Models, for which the profile can be accurately estimated using Monte Carlo methods. We then show how Bend and Mix Models can be used to study the limitations of existing mutual information estimators, investigate the behavior of neural critics used in variational estimators, and understand the effect of experimental outliers on mutual information estimation. Finally, we show how Bend and Mix Models can be used to obtain model-based Bayesian estimates of mutual information, suitable for problems with available domain expertise in which uncertainty quantification is necessary.
title On the Properties and Estimation of Pointwise Mutual Information Profiles
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2310.10240