Mutual Information Estimation via $f$-Divergence and Data Derangements

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Letizia, Nunzio A., Novello, Nicola, Tonello, Andrea M.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913575797260288
author Letizia, Nunzio A.
Novello, Nicola
Tonello, Andrea M.
author_facet Letizia, Nunzio A.
Novello, Nicola
Tonello, Andrea M.
contents Estimating mutual information accurately is pivotal across diverse applications, from machine learning to communications and biology, enabling us to gain insights into the inner mechanisms of complex systems. Yet, dealing with high-dimensional data presents a formidable challenge, due to its size and the presence of intricate relationships. Recently proposed neural methods employing variational lower bounds on the mutual information have gained prominence. However, these approaches suffer from either high bias or high variance, as the sample size and the structure of the loss function directly influence the training process. In this paper, we propose a novel class of discriminative mutual information estimators based on the variational representation of the $f$-divergence. We investigate the impact of the permutation function used to obtain the marginal training samples and present a novel architectural solution based on derangements. The proposed estimator is flexible since it exhibits an excellent bias/variance trade-off. The comparison with state-of-the-art neural estimators, through extensive experimentation within established reference scenarios, shows that our approach offers higher accuracy and lower complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2305_20025
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Mutual Information Estimation via $f$-Divergence and Data Derangements
Letizia, Nunzio A.
Novello, Nicola
Tonello, Andrea M.
Machine Learning
Information Theory
Signal Processing
Estimating mutual information accurately is pivotal across diverse applications, from machine learning to communications and biology, enabling us to gain insights into the inner mechanisms of complex systems. Yet, dealing with high-dimensional data presents a formidable challenge, due to its size and the presence of intricate relationships. Recently proposed neural methods employing variational lower bounds on the mutual information have gained prominence. However, these approaches suffer from either high bias or high variance, as the sample size and the structure of the loss function directly influence the training process. In this paper, we propose a novel class of discriminative mutual information estimators based on the variational representation of the $f$-divergence. We investigate the impact of the permutation function used to obtain the marginal training samples and present a novel architectural solution based on derangements. The proposed estimator is flexible since it exhibits an excellent bias/variance trade-off. The comparison with state-of-the-art neural estimators, through extensive experimentation within established reference scenarios, shows that our approach offers higher accuracy and lower complexity.
title Mutual Information Estimation via $f$-Divergence and Data Derangements
topic Machine Learning
Information Theory
Signal Processing
url https://arxiv.org/abs/2305.20025