Leveraging joint sparsity in hierarchical Bayesian learning

DOI10.1137/23M156255XMaRDI QIDQ6431334zbMATH OpenFDO

Authors Jan Glaubitz, Anne Gelb

Publication date 29 March 2023

Full work available at URL https://doi.org/10.1137/23M156255X

Mathematics Subject Classification ID

Bayesian inference (62F15) Ill-posedness and regularization problems in numerical linear algebra (65F22) Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10)

Abstract: 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.

Recommendations

• Overcomplete representation in a hierarchical Bayesian framework
• Computationally efficient sampling methods for sparsity promoting hierarchical Bayesian models
• Bayesian hierarchical dictionary learning
• Bayesian sparse estimation using double Lomax priors

Cited in

(6)

• Hyperparameter estimation for sparse Bayesian learning models
• Hierarchical Bayesian inverse problems: a high-dimensional statistics viewpoint
• Efficient sparsity-promoting MAP estimation for Bayesian linear inverse problems
• Efficient sampling for sparse Bayesian learning using hierarchical prior normalization
• Bayesian decomposition using Besov priors
• The Bayesian SIAC filter

This page was built for publication: Leveraging joint sparsity in hierarchical Bayesian learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6431334)