Saved in:
Bibliographic Details
Main Authors: Nielsen, Frank, Okamura, Kazuki
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2204.10952
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916095571525632
author Nielsen, Frank
Okamura, Kazuki
author_facet Nielsen, Frank
Okamura, Kazuki
contents We first extend the result of Ali and Silvey [Journal of the Royal Statistical Society: Series B, 28.1 (1966), 131-142] who first reported that any $f$-divergence between two isotropic multivariate Gaussian distributions amounts to a corresponding strictly increasing scalar function of their corresponding Mahalanobis distance. We report sufficient conditions on the standard probability density function generating a multivariate location family and the function generator $f$ in order to generalize this result. This property is useful in practice as it allows to compare exactly $f$-divergences between densities of these location families via their corresponding Mahalanobis distances, even when the $f$-divergences are not available in closed-form as it is the case, for example, for the Jensen-Shannon divergence or the total variation distance between densities of a normal location family. Second, we consider $f$-divergences between densities of multivariate scale families: We recall Ali and Silvey 's result that for normal scale families we get matrix spectral divergences, and we extend this result to densities of a scale family.
format Preprint
id arxiv_https___arxiv_org_abs_2204_10952
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A note on the $f$-divergences between multivariate location-scale families with either prescribed scale matrices or location parameters
Nielsen, Frank
Okamura, Kazuki
Statistics Theory
Information Theory
We first extend the result of Ali and Silvey [Journal of the Royal Statistical Society: Series B, 28.1 (1966), 131-142] who first reported that any $f$-divergence between two isotropic multivariate Gaussian distributions amounts to a corresponding strictly increasing scalar function of their corresponding Mahalanobis distance. We report sufficient conditions on the standard probability density function generating a multivariate location family and the function generator $f$ in order to generalize this result. This property is useful in practice as it allows to compare exactly $f$-divergences between densities of these location families via their corresponding Mahalanobis distances, even when the $f$-divergences are not available in closed-form as it is the case, for example, for the Jensen-Shannon divergence or the total variation distance between densities of a normal location family. Second, we consider $f$-divergences between densities of multivariate scale families: We recall Ali and Silvey 's result that for normal scale families we get matrix spectral divergences, and we extend this result to densities of a scale family.
title A note on the $f$-divergences between multivariate location-scale families with either prescribed scale matrices or location parameters
topic Statistics Theory
Information Theory
url https://arxiv.org/abs/2204.10952