• DocumentCode
    51312
  • Title

    Efficient High-Dimensional Inference in the Multiple Measurement Vector Problem

  • Author

    Ziniel, Justin ; Schniter, Philip

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Ohio State Univ., Columbus, OH, USA
  • Volume
    61
  • Issue
    2
  • fYear
    2013
  • fDate
    Jan.15, 2013
  • Firstpage
    340
  • Lastpage
    354
  • Abstract
    In this work, a Bayesian approximate message passing algorithm is proposed for solving the multiple measurement vector (MMV) problem in compressive sensing, in which a collection of sparse signal vectors that share a common support are recovered from undersampled noisy measurements. The algorithm, AMP-MMV, is capable of exploiting temporal correlations in the amplitudes of non-zero coefficients, and provides soft estimates of the signal vectors as well as the underlying support. Central to the proposed approach is an extension of recently developed approximate message passing techniques to the amplitude-correlated MMV setting. Aided by these techniques, AMP-MMV offers a computational complexity that is linear in all problem dimensions. In order to allow for automatic parameter tuning, an expectation-maximization algorithm that complements AMP-MMV is described. Finally, a detailed numerical study demonstrates the power of the proposed approach and its particular suitability for application to high-dimensional problems.
  • Keywords
    Bayes methods; compressed sensing; expectation-maximisation algorithm; vectors; AMP-MMV; Bayesian approximate message passing algorithm; amplitude-correlated MMV setting; automatic parameter tuning; compressive sensing; expectation-maximization algorithm; high-dimensional inference; multiple measurement vector problem; sparse signal vector; temporal correlation; Approximation algorithms; Bayesian methods; Complexity theory; Correlation; Joints; Noise measurement; Vectors; Approximate message passing (AMP); Kalman filters; belief propagation; compressed sensing; expectation-maximization algorithms; joint sparsity; multiple measurement vector problem; statistical signal processing;
  • fLanguage
    English
  • Journal_Title
    Signal Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1053-587X
  • Type

    jour

  • DOI
    10.1109/TSP.2012.2222382
  • Filename
    6320709