On the entropy and information of Gaussian mixtures

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Eskenazis, Alexandros, Gavalakis, Lampros
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916127412584448
author Eskenazis, Alexandros
Gavalakis, Lampros
author_facet Eskenazis, Alexandros
Gavalakis, Lampros
contents We establish several convexity properties for the entropy and Fisher information of mixtures of centered Gaussian distributions. First, we prove that if $X_1, X_2$ are independent scalar Gaussian mixtures, then the entropy of $\sqrt{t}X_1 + \sqrt{1-t}X_2$ is concave in $t \in [0,1]$, thus confirming a conjecture of Ball, Nayar and Tkocz (2016) for this class of random variables. In fact, we prove a generalisation of this assertion which also strengthens a result of Eskenazis, Nayar and Tkocz (2018). For the Fisher information, we extend a convexity result of Bobkov (2022) by showing that the Fisher information matrix is operator convex as a matrix-valued function acting on densities of mixtures in $\mathbb{R}^d$. As an application, we establish rates for the convergence of the Fisher information matrix of the sum of weighted i.i.d. Gaussian mixtures in the operator norm along the central limit theorem under mild moment assumptions.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15997
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the entropy and information of Gaussian mixtures
Eskenazis, Alexandros
Gavalakis, Lampros
Information Theory
Probability
94A17 (Primary) 60E15, 26B25 (Secondary)
We establish several convexity properties for the entropy and Fisher information of mixtures of centered Gaussian distributions. First, we prove that if $X_1, X_2$ are independent scalar Gaussian mixtures, then the entropy of $\sqrt{t}X_1 + \sqrt{1-t}X_2$ is concave in $t \in [0,1]$, thus confirming a conjecture of Ball, Nayar and Tkocz (2016) for this class of random variables. In fact, we prove a generalisation of this assertion which also strengthens a result of Eskenazis, Nayar and Tkocz (2018). For the Fisher information, we extend a convexity result of Bobkov (2022) by showing that the Fisher information matrix is operator convex as a matrix-valued function acting on densities of mixtures in $\mathbb{R}^d$. As an application, we establish rates for the convergence of the Fisher information matrix of the sum of weighted i.i.d. Gaussian mixtures in the operator norm along the central limit theorem under mild moment assumptions.
title On the entropy and information of Gaussian mixtures
topic Information Theory
Probability
94A17 (Primary) 60E15, 26B25 (Secondary)
url https://arxiv.org/abs/2308.15997