Information Theory Measures via Multidimensional Gaussianization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Laparra, Valero, Johnson, J. Emmanuel, Camps-Valls, Gustau, Santos-Rodríguez, Raul, Malo, Jesus
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912091475017728
author Laparra, Valero
Johnson, J. Emmanuel
Camps-Valls, Gustau
Santos-Rodríguez, Raul
Malo, Jesus
author_facet Laparra, Valero
Johnson, J. Emmanuel
Camps-Valls, Gustau
Santos-Rodríguez, Raul
Malo, Jesus
contents Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems. It has several desirable properties for real world applications: it naturally deals with multivariate data, it can handle heterogeneous data types, and the measures can be interpreted in physical units. However, it has not been adopted by a wider audience because obtaining information from multidimensional data is a challenging problem due to the curse of dimensionality. Here we propose an indirect way of computing information based on a multivariate Gaussianization transform. Our proposal mitigates the difficulty of multivariate density estimation by reducing it to a composition of tractable (marginal) operations and simple linear transformations, which can be interpreted as a particular deep neural network. We introduce specific Gaussianization-based methodologies to estimate total correlation, entropy, mutual information and Kullback-Leibler divergence. We compare them to recent estimators showing the accuracy on synthetic data generated from different multivariate distributions. We made the tools and datasets publicly available to provide a test-bed to analyze future methodologies. Results show that our proposal is superior to previous estimators particularly in high-dimensional scenarios; and that it leads to interesting insights in neuroscience, geoscience, computer vision, and machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2010_03807
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Information Theory Measures via Multidimensional Gaussianization
Laparra, Valero
Johnson, J. Emmanuel
Camps-Valls, Gustau
Santos-Rodríguez, Raul
Malo, Jesus
Machine Learning
Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems. It has several desirable properties for real world applications: it naturally deals with multivariate data, it can handle heterogeneous data types, and the measures can be interpreted in physical units. However, it has not been adopted by a wider audience because obtaining information from multidimensional data is a challenging problem due to the curse of dimensionality. Here we propose an indirect way of computing information based on a multivariate Gaussianization transform. Our proposal mitigates the difficulty of multivariate density estimation by reducing it to a composition of tractable (marginal) operations and simple linear transformations, which can be interpreted as a particular deep neural network. We introduce specific Gaussianization-based methodologies to estimate total correlation, entropy, mutual information and Kullback-Leibler divergence. We compare them to recent estimators showing the accuracy on synthetic data generated from different multivariate distributions. We made the tools and datasets publicly available to provide a test-bed to analyze future methodologies. Results show that our proposal is superior to previous estimators particularly in high-dimensional scenarios; and that it leads to interesting insights in neuroscience, geoscience, computer vision, and machine learning.
title Information Theory Measures via Multidimensional Gaussianization
topic Machine Learning
url https://arxiv.org/abs/2010.03807