Saved in:
Bibliographic Details
Main Authors: Sevilla, Martín, Marques, Antonio García, Segarra, Santiago
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.14340
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914689524432896
author Sevilla, Martín
Marques, Antonio García
Segarra, Santiago
author_facet Sevilla, Martín
Marques, Antonio García
Segarra, Santiago
contents We propose a novel algorithm for the support estimation of partially known Gaussian graphical models that incorporates prior information about the underlying graph. In contrast to classical approaches that provide a point estimate based on a maximum likelihood or a maximum a posteriori criterion using (simple) priors on the precision matrix, we consider a prior on the graph and rely on annealed Langevin diffusion to generate samples from the posterior distribution. Since the Langevin sampler requires access to the score function of the underlying graph prior, we use graph neural networks to effectively estimate the score from a graph dataset (either available beforehand or generated from a known distribution). Numerical experiments demonstrate the benefits of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14340
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Estimation of partially known Gaussian graphical models with score-based structural priors
Sevilla, Martín
Marques, Antonio García
Segarra, Santiago
Machine Learning
We propose a novel algorithm for the support estimation of partially known Gaussian graphical models that incorporates prior information about the underlying graph. In contrast to classical approaches that provide a point estimate based on a maximum likelihood or a maximum a posteriori criterion using (simple) priors on the precision matrix, we consider a prior on the graph and rely on annealed Langevin diffusion to generate samples from the posterior distribution. Since the Langevin sampler requires access to the score function of the underlying graph prior, we use graph neural networks to effectively estimate the score from a graph dataset (either available beforehand or generated from a known distribution). Numerical experiments demonstrate the benefits of our approach.
title Estimation of partially known Gaussian graphical models with score-based structural priors
topic Machine Learning
url https://arxiv.org/abs/2401.14340