On the gap between RIP-properties and sparse recovery conditions

We consider the problem of recovering sparse vectors from underdetermined linear measurements via $\ell_p$-constrained basis pursuit. Previous analyses of this problem based on generalized restricted isometry properties have suggested that two phenomena occur if $p\neq 2$. First, one may need substantially more than $s \log(en/s)$ measurements (optimal for $p=2$) for uniform recovery of all $s$-sparse vectors. Second, the matrix that achieves recovery with the optimal number of measurements may not be Gaussian (as for $p=2$). We present a new, direct analysis which shows that in fact neither of these phenomena occur. Via a suitable version of the null space property we show that a standard Gaussian matrix provides $\ell_q/\ell_1$-recovery guarantees for $\ell_p$-constrained basis pursuit in the optimal measurement regime. Our result extends to several heavier-tailed measurement matrices. As an application, we show that one can obtain a consistent reconstruction from uniform scalar quantized measurements in the optimal measurement regime.

[1]  E. Milman,et al.  Remarks on the KLS conjecture and Hardy-type inequalities , 2014, 1405.0617.

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

[3]  Holger Rauhut,et al.  Analysis ℓ1-recovery with Frames and Gaussian Measurements , 2015, ArXiv.

[4]  A. Pinkus n-Widths in Approximation Theory , 1985 .

[5]  Zeyuan Allen Zhu,et al.  Restricted Isometry Property for General p-Norms , 2014, IEEE Transactions on Information Theory.

[6]  S. Mendelson Learning without concentration for general loss functions , 2014, 1410.3192.

[7]  M. Rudelson,et al.  On sparse reconstruction from Fourier and Gaussian measurements , 2008 .

[8]  R. Adamczak,et al.  Geometry of log-concave Ensembles of random matrices and approximate reconstruction , 2011, 1103.0401.

[9]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[10]  S. Mendelson,et al.  Compressed sensing under weak moment assumptions , 2014, 1401.2188.

[11]  Jean-Jacques Fuchs,et al.  Fast implementation of a ℓ1 - ℓ1 regularized sparse representations algorithm. , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  慧 廣瀬 A Mathematical Introduction to Compressive Sensing , 2015 .

[13]  S. Foucart Stability and robustness of ℓ1-minimizations with Weibull matrices and redundant dictionaries , 2014 .

[14]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[15]  Venkat Chandar,et al.  Sparse graph codes for compression, sensing, and secrecy , 2010 .

[16]  Piotr Indyk,et al.  Combining geometry and combinatorics: A unified approach to sparse signal recovery , 2008, 2008 46th Annual Allerton Conference on Communication, Control, and Computing.

[17]  Laurent Jacques,et al.  Quantization and Compressive Sensing , 2014, ArXiv.

[18]  S. Mendelson,et al.  Reconstruction and Subgaussian Operators in Asymptotic Geometric Analysis , 2007 .

[19]  Holger Rauhut,et al.  A Mathematical Introduction to Compressive Sensing , 2013, Applied and Numerical Harmonic Analysis.

[20]  Fedor Nazarov,et al.  On Convex Bodies and Log-Concave Probability Measures with Unconditional Basis , 2003 .

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

[22]  V. Koltchinskii,et al.  Bounding the smallest singular value of a random matrix without concentration , 2013, 1312.3580.

[23]  Balas K. Natarajan,et al.  Sparse Approximate Solutions to Linear Systems , 1995, SIAM J. Comput..

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

[25]  R. Adamczak,et al.  Restricted Isometry Property of Matrices with Independent Columns and Neighborly Polytopes by Random Sampling , 2009, 0904.4723.

[26]  V. Koltchinskii,et al.  Oracle inequalities in empirical risk minimization and sparse recovery problems , 2011 .

[27]  Shahar Mendelson,et al.  Learning without Concentration , 2014, COLT.

[28]  S. Mendelson A remark on the diameter of random sections of convex bodies , 2013, 1312.3608.

[29]  Djalil CHAFAÏ,et al.  Circular law for random matrices with unconditional log-concave distribution , 2013, 1303.5838.

[30]  Rafal Latala On Weak Tail Domination of Random Vectors , 2007 .