Near Oracle Performance of Signal Space Greedy Methods

Compressive sampling (CoSa) is a new methodology which demonstrates that sparse signals can be recovered from a small number of linear measurements. Greedy algorithms like CoSaMP have been designed for this recovery, and variants of these methods have been adapted to the case where sparsity is with respect to some arbitrary dictionary rather than an orthonormal basis. In this work we present an analysis of this so-called Signal Space CoSaMP method when the measurements are corrupted with mean-zero white Gaussian noise. We establish near-oracle performance for recovery of signals sparse in some arbitrary dictionary.

[1]  Pierre Vandergheynst,et al.  Compressed Sensing and Redundant Dictionaries , 2007, IEEE Transactions on Information Theory.

[2]  Raja Giryes,et al.  Greedy Signal Space Methods for incoherence and beyond , 2013, ArXiv.

[3]  Michael Elad,et al.  Analysis versus synthesis in signal priors , 2006, 2006 14th European Signal Processing Conference.

[4]  Michael Elad,et al.  Iterative Hard Thresholding with Near Optimal Projection for Signal Recovery , 2013 .

[5]  I. Johnstone,et al.  Ideal denoising in an orthonormal basis chosen from a library of bases , 1994 .

[6]  P. Bickel,et al.  SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.

[7]  Deanna Needell,et al.  Signal Space CoSaMP for Sparse Recovery With Redundant Dictionaries , 2012, IEEE Transactions on Information Theory.

[8]  Emmanuel J. Cand.  Modern statistical estimation via oracle inequalities , 2006 .

[9]  V. Milman,et al.  Asymptotic Theory Of Finite Dimensional Normed Spaces , 1986 .

[10]  Simon Foucart,et al.  Hard Thresholding Pursuit: An Algorithm for Compressive Sensing , 2011, SIAM J. Numer. Anal..

[11]  Deanna Needell,et al.  CoSaMP: Iterative signal recovery from incomplete and inaccurate samples , 2008, ArXiv.

[12]  Emmanuel J. Candès,et al.  Decoding by linear programming , 2005, IEEE Transactions on Information Theory.

[13]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[14]  Michael B. Wakin,et al.  Compressive Sensing of Analog Signals Using Discrete Prolate Spheroidal Sequences , 2011, ArXiv.

[15]  Terence Tao,et al.  The Dantzig selector: Statistical estimation when P is much larger than n , 2005, math/0506081.

[16]  Emmanuel J. Candès,et al.  Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies? , 2004, IEEE Transactions on Information Theory.

[17]  S. Mendelson,et al.  Uniform Uncertainty Principle for Bernoulli and Subgaussian Ensembles , 2006, math/0608665.

[18]  Thomas Blumensath,et al.  Sampling and Reconstructing Signals From a Union of Linear Subspaces , 2009, IEEE Transactions on Information Theory.

[19]  Yonina C. Eldar,et al.  Compressed Sensing with Coherent and Redundant Dictionaries , 2010, ArXiv.

[20]  M. Davies,et al.  Greedy-like algorithms for the cosparse analysis model , 2012, 1207.2456.

[21]  Mike E. Davies,et al.  Iterative Hard Thresholding for Compressed Sensing , 2008, ArXiv.

[22]  Michael Elad,et al.  RIP-Based Near-Oracle Performance Guarantees for SP, CoSaMP, and IHT , 2012, IEEE Transactions on Signal Processing.

[23]  S. Foucart.  Sparse Recovery Algorithms: Sufficient Conditions in Terms of RestrictedIsometry Constants , 2012 .

[24]  G. Pisier.  Probabilistic methods in the geometry of Banach spaces , 1986 .