Saved in:
Bibliographic Details
Main Authors: Mastrantonio, Gianluca, Di Loro, Pierfrancesco Alaimo, Mingione, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916790610690048
author Mastrantonio, Gianluca
Di Loro, Pierfrancesco Alaimo
Mingione, Marco
author_facet Mastrantonio, Gianluca
Di Loro, Pierfrancesco Alaimo
Mingione, Marco
contents We introduce a general strategy for defining distributions over the space of sparse symmetric positive definite matrices. Our method utilizes the Cholesky factorization of the precision matrix, imposing sparsity through constraints on its elements while preserving their independence and avoiding the numerical evaluation of normalization constants. In particular, we develop the S-Bartlett as a modified Bartlett decomposition, recovering the standard Wishart as a particular case. By incorporating a Spike-and-Slab prior to model graph sparsity, our approach facilitates Bayesian estimation through a tailored MCMC routine based on a Dual Averaging Hamiltonian Monte Carlo update. This framework extends naturally to the Generalized Linear Model setting, enabling applications to non-Gaussian outcomes via latent Gaussian variables. We test and compare the proposed S-Bartelett prior with the G-Wishart both on simulated and real data. Results highlight that the S-Bartlett prior offers a flexible alternative for estimating sparse precision matrices, with potential applications across diverse fields.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09607
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A new hierarchical distribution on arbitrary sparse precision matrices
Mastrantonio, Gianluca
Di Loro, Pierfrancesco Alaimo
Mingione, Marco
Methodology
Computation
We introduce a general strategy for defining distributions over the space of sparse symmetric positive definite matrices. Our method utilizes the Cholesky factorization of the precision matrix, imposing sparsity through constraints on its elements while preserving their independence and avoiding the numerical evaluation of normalization constants. In particular, we develop the S-Bartlett as a modified Bartlett decomposition, recovering the standard Wishart as a particular case. By incorporating a Spike-and-Slab prior to model graph sparsity, our approach facilitates Bayesian estimation through a tailored MCMC routine based on a Dual Averaging Hamiltonian Monte Carlo update. This framework extends naturally to the Generalized Linear Model setting, enabling applications to non-Gaussian outcomes via latent Gaussian variables. We test and compare the proposed S-Bartelett prior with the G-Wishart both on simulated and real data. Results highlight that the S-Bartlett prior offers a flexible alternative for estimating sparse precision matrices, with potential applications across diverse fields.
title A new hierarchical distribution on arbitrary sparse precision matrices
topic Methodology
Computation
url https://arxiv.org/abs/2506.09607