Saved in:
Bibliographic Details
Main Authors: Joudeh, Basheer, Škorić, Boris
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.07311
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909486713667584
author Joudeh, Basheer
Škorić, Boris
author_facet Joudeh, Basheer
Škorić, Boris
contents We calculate the average differential entropy of a $q$-component Gaussian mixture in $\mathbb R^n$. For simplicity, all components have covariance matrix $σ^2 {\mathbf 1}$, while the means $\{\mathbf{W}_i\}_{i=1}^{q}$ are i.i.d. Gaussian vectors with zero mean and covariance $s^2 {\mathbf 1}$. We obtain a series expansion in $μ=s^2/σ^2$ for the average differential entropy up to order $\mathcal{O}(μ^2)$, and we provide a recipe to calculate higher order terms. Our result provides an analytic approximation with a quantifiable order of magnitude for the error, which is not achieved in previous literature.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07311
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Average entropy of Gaussian mixtures
Joudeh, Basheer
Škorić, Boris
Information Theory
We calculate the average differential entropy of a $q$-component Gaussian mixture in $\mathbb R^n$. For simplicity, all components have covariance matrix $σ^2 {\mathbf 1}$, while the means $\{\mathbf{W}_i\}_{i=1}^{q}$ are i.i.d. Gaussian vectors with zero mean and covariance $s^2 {\mathbf 1}$. We obtain a series expansion in $μ=s^2/σ^2$ for the average differential entropy up to order $\mathcal{O}(μ^2)$, and we provide a recipe to calculate higher order terms. Our result provides an analytic approximation with a quantifiable order of magnitude for the error, which is not achieved in previous literature.
title Average entropy of Gaussian mixtures
topic Information Theory
url https://arxiv.org/abs/2404.07311