Leveraging joint sparsity in hierarchical Bayesian learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Glaubitz, Jan, Gelb, Anne
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909209539379200
author Glaubitz, Jan
Gelb, Anne
author_facet Glaubitz, Jan
Gelb, Anne
contents We present a hierarchical Bayesian learning approach to infer jointly sparse parameter vectors from multiple measurement vectors. Our model uses separate conditionally Gaussian priors for each parameter vector and common gamma-distributed hyper-parameters to enforce joint sparsity. The resulting joint-sparsity-promoting priors are combined with existing Bayesian inference methods to generate a new family of algorithms. Our numerical experiments, which include a multi-coil magnetic resonance imaging application, demonstrate that our new approach consistently outperforms commonly used hierarchical Bayesian methods.
format Preprint
id arxiv_https___arxiv_org_abs_2303_16954
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Leveraging joint sparsity in hierarchical Bayesian learning
Glaubitz, Jan
Gelb, Anne
Machine Learning
Numerical Analysis
65F22, 62F15, 65K10, 68U10
We present a hierarchical Bayesian learning approach to infer jointly sparse parameter vectors from multiple measurement vectors. Our model uses separate conditionally Gaussian priors for each parameter vector and common gamma-distributed hyper-parameters to enforce joint sparsity. The resulting joint-sparsity-promoting priors are combined with existing Bayesian inference methods to generate a new family of algorithms. Our numerical experiments, which include a multi-coil magnetic resonance imaging application, demonstrate that our new approach consistently outperforms commonly used hierarchical Bayesian methods.
title Leveraging joint sparsity in hierarchical Bayesian learning
topic Machine Learning
Numerical Analysis
65F22, 62F15, 65K10, 68U10
url https://arxiv.org/abs/2303.16954