Log-concave density estimation in undirected graphical models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kubjas, Kaie, Kuznetsova, Olga, Robeva, Elina, Semnani, Pardis, Sodomaco, Luca
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909935048065024
author Kubjas, Kaie
Kuznetsova, Olga
Robeva, Elina
Semnani, Pardis
Sodomaco, Luca
author_facet Kubjas, Kaie
Kuznetsova, Olga
Robeva, Elina
Semnani, Pardis
Sodomaco, Luca
contents We study the problem of maximum likelihood estimation of densities that are log-concave and lie in the graphical model corresponding to a given undirected graph $G$. We show that the maximum likelihood estimate (MLE) is the product of the exponentials of several tent functions, one for each maximal clique of $G$. While the set of log-concave densities in a graphical model is infinite-dimensional, our results imply that the MLE can be found by solving a finite-dimensional convex optimization problem. We provide an implementation and a few examples. Furthermore, we show that the MLE exists and is unique with probability 1 as long as the number of sample points is larger than the size of the largest clique of $G$ when $G$ is chordal. We show that the MLE is consistent when the graph $G$ is a disjoint union of cliques. Finally, we discuss the conditions under which a log-concave density in the graphical model of $G$ has a log-concave factorization according to $G$.
format Preprint
id arxiv_https___arxiv_org_abs_2206_05227
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Log-concave density estimation in undirected graphical models
Kubjas, Kaie
Kuznetsova, Olga
Robeva, Elina
Semnani, Pardis
Sodomaco, Luca
Statistics Theory
Computation
Methodology
Machine Learning
62G05, 62H22, 62H12, 26B25
We study the problem of maximum likelihood estimation of densities that are log-concave and lie in the graphical model corresponding to a given undirected graph $G$. We show that the maximum likelihood estimate (MLE) is the product of the exponentials of several tent functions, one for each maximal clique of $G$. While the set of log-concave densities in a graphical model is infinite-dimensional, our results imply that the MLE can be found by solving a finite-dimensional convex optimization problem. We provide an implementation and a few examples. Furthermore, we show that the MLE exists and is unique with probability 1 as long as the number of sample points is larger than the size of the largest clique of $G$ when $G$ is chordal. We show that the MLE is consistent when the graph $G$ is a disjoint union of cliques. Finally, we discuss the conditions under which a log-concave density in the graphical model of $G$ has a log-concave factorization according to $G$.
title Log-concave density estimation in undirected graphical models
topic Statistics Theory
Computation
Methodology
Machine Learning
62G05, 62H22, 62H12, 26B25
url https://arxiv.org/abs/2206.05227