Bayesian approach with extended support estimation for sparse linear regression

DOI10.1016/J.RINAM.2019.100012MaRDI QIDQ2211053zbMATH OpenOpenAlexFDO

Authors Kyung Su Kim, Sae-Young Chung

Publication date 10 November 2020

Published in Results in Applied Mathematics (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://arxiv.org/abs/1904.01818

zbMATH Keywords

compressed sensingmaximum a posteriorisparse linear regressionextended support estimationmultiple support candidates

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: A greedy algorithm called Bayesian multiple matching pursuit (BMMP) is proposed to estimate a sparse signal vector and its support given $m$ linear measurements. Unlike the maximum a posteriori (MAP) support detection, which was proposed by Lee to estimate the support by selecting an index with the maximum likelihood ratio of the correlation given by a normalized version of the orthogonal matching pursuit (OMP), the proposed method uses the correlation given by the matching pursuit proposed by Davies and Eldar. BMMP exploits the diversity gain to estimate the support by considering multiple support candidates, each of which is obtained by iteratively selecting an index set with a size different for each candidate. In particular, BMMP considers an extended support estimate whose maximal size is $m$ in the process to obtain each of the support candidates. It is observed that BMMP outperforms other state-of-the-art methods and approaches the ideal limit of the signal sparsity in our simulation setting.

Recommendations

• Binary sparse signal recovery with binary matching pursuit
• Hierachical Bayesian models and sparsity: \(\ell_2\)-magic
• Recovery of sparse signals by orthogonal multi-matching pursuit
• Arbitrary block-sparse signal reconstruction based on incomplete single measurement vector
• Sparse signal recovery via ECME thresholding pursuits

Cites work

• A mathematical introduction to compressive sensing
• CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
• Compressed sensing
• Compressive sampling
• From Denoising to Compressed Sensing
• Fundamentals of Wireless Communication
• Generalized Orthogonal Matching Pursuit
• Image Super-Resolution Via Sparse Representation
• MAP Support Detection for Greedy Sparse Signal Recovery Algorithms in Compressive Sensing
• Multipath Matching Pursuit
• Rank Awareness in Joint Sparse Recovery
• Sparse Bayesian Learning for Basis Selection
• Subspace Pursuit for Compressive Sensing Signal Reconstruction
• Super-resolution radar

Cited in

(1)

• Sparse Bayesian linear regression using generalized normal priors

Describes a project that uses

Uses Software

• CoSaMP

This page was built for publication: Bayesian approach with extended support estimation for sparse linear regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2211053)