Quasi-sparsest solutions for quantized compressed sensing by graduated-non-convexity based reweighted ℓ1 minimization

In this paper, we address the problem of sparse signal recovery from scalar quantized compressed sensing measurements, via optimization. To compensate for compression losses due to dimensionality reduction and quantization, we consider a cost function that is more sparsity-inducing than the commonly used ℓ1-norm. Besides, we enforce a quantization consistency constraint that naturally handles the saturation issue. We investigate the potential of the recent Graduated-Non-Convexity based reweighted ℓ1-norm minimization for sparse recovery over polyhedral sets. We demonstrate by simulations, the robustness of the proposed approach towards saturation and its significant performance gain, in terms of reconstruction accuracy and support recovery capability.

[1]  24th European Signal Processing Conference, EUSIPCO 2016, Budapest, Hungary, August 29 - September 2, 2016 , 2016, European Signal Processing Conference.

[2]  Richard G. Baraniuk,et al.  Robust support recovery using sparse compressive sensing matrices , 2011, 2011 45th Annual Conference on Information Sciences and Systems.

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

[4]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[5]  Richard G. Baraniuk,et al.  Democracy in Action: Quantization, Saturation, and Compressive Sensing , 2011 .

[6]  Massoud Babaie-Zadeh,et al.  Successive Concave Sparsity Approximation: Near-Oracle Performance in a Wide Range of Sparsity Levels , 2015, ArXiv.

[7]  Laurent Jacques,et al.  Dequantizing Compressed Sensing: When Oversampling and Non-Gaussian Constraints Combine , 2009, IEEE Transactions on Information Theory.

[8]  Olvi L. Mangasarian,et al.  Machine Learning via Polyhedral Concave Minimization , 1996 .

[9]  Tangi Migot,et al.  A Smoothing Method for Sparse Optimization over Polyhedral Sets , 2015, MCO.

[10]  Prateek Jain,et al.  One-Bit Compressed Sensing: Provable Support and Vector Recovery , 2013, ICML.

[11]  Pramod K. Varshney,et al.  Performance Bounds for Sparsity Pattern Recovery With Quantized Noisy Random Projections , 2012, IEEE Journal of Selected Topics in Signal Processing.

[12]  Stephen P. Boyd,et al.  Enhancing Sparsity by Reweighted ℓ1 Minimization , 2007, 0711.1612.

[13]  Cishen Zhang,et al.  Variational Bayesian Algorithm for Quantized Compressed Sensing , 2012, IEEE Transactions on Signal Processing.

[14]  Ivan W. Selesnick,et al.  Sparse Signal Estimation by Maximally Sparse Convex Optimization , 2013, IEEE Transactions on Signal Processing.

[15]  Stephen P. Boyd,et al.  Compressed Sensing With Quantized Measurements , 2010, IEEE Signal Processing Letters.

[16]  Laurent Jacques,et al.  Consistent Basis Pursuit for Signal and Matrix Estimates in Quantized Compressed Sensing , 2015, IEEE Signal Processing Letters.

[17]  Christian Jutten,et al.  A Fast Approach for Overcomplete Sparse Decomposition Based on Smoothed $\ell ^{0}$ Norm , 2008, IEEE Transactions on Signal Processing.

[18]  Olgica Milenkovic,et al.  Information Theoretical and Algorithmic Approaches to Quantized Compressive Sensing , 2011, IEEE Transactions on Communications.

[19]  Bhaskar D. Rao,et al.  An affine scaling methodology for best basis selection , 1999, IEEE Trans. Signal Process..

[20]  Rayan Saab,et al.  Sobolev Duals for Random Frames and ΣΔ Quantization of Compressed Sensing Measurements , 2013, Found. Comput. Math..