RIPless compressed sensing from anisotropic measurements

Abstract Compressed sensing is the art of reconstructing a sparse vector from its inner products with respect to a small set of randomly chosen measurement vectors. It is usually assumed that the ensemble of measurement vectors is in isotropic position in the sense that the associated covariance matrix is proportional to the identity matrix. In this paper, we establish bounds on the number of required measurements in the anisotropic case, where the ensemble of measurement vectors possesses a non-trivial covariance matrix. Essentially, we find that the required sampling rate grows proportionally to the condition number of the covariance matrix. In contrast to other recent contributions to this problem, our arguments do not rely on any restricted isometry properties (RIP’s), but rather on ideas from convex geometry which have been systematically studied in the theory of low-rank matrix recovery. This allows for a simple argument and slightly improved bounds, but may lead to a worse dependency on noise (which we do not consider in the present paper).

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

[2]  P. Bickel.  Discussion: The Dantzig selector: Statistical estimation when p is much larger than n , 2007, 0803.3124.

[3]  David Gross,et al.  Recovering Low-Rank Matrices From Few Coefficients in Any Basis , 2009, IEEE Transactions on Information Theory.

[4]  Emmanuel J. Candès,et al.  Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements , 2011, IEEE Transactions on Information Theory.

[5]  Stephen Becker,et al.  Quantum state tomography via compressed sensing. , 2009, Physical review letters.

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

[7]  Shuheng Zhou,et al.  25th Annual Conference on Learning Theory Reconstruction from Anisotropic Random Measurements , 2022 .

[8]  Dimitri P. Bertsekas,et al.  Convex Analysis and Optimization , 2003 .

[9]  M. Habib.  Probabilistic methods for algorithmic discrete mathematics , 1998 .

[10]  V. Temlyakov,et al.  A remark on Compressed Sensing , 2007 .

[11]  Arkadi Nemirovski,et al.  On verifiable sufficient conditions for sparse signal recovery via ℓ1 minimization , 2008, Math. Program..

[12]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[13]  Martin J. Wainwright,et al.  Restricted strong convexity and weighted matrix completion: Optimal bounds with noise , 2010, J. Mach. Learn. Res..

[14]  Emmanuel J. Candès,et al.  A Probabilistic and RIPless Theory of Compressed Sensing , 2010, IEEE Transactions on Information Theory.

[15]  Rudolf Ahlswede,et al.  Strong converse for identification via quantum channels , 2000, IEEE Trans. Inf. Theory.

[16]  Vincent Nesme,et al.  Continuous-variable quantum compressed sensing , 2011, 1111.0853.

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

[18]  Yi-Kai Liu,et al.  Universal low-rank matrix recovery from Pauli measurements , 2011, NIPS.

[19]  Steven T. Flammia,et al.  Quantum tomography via compressed sensing: error bounds, sample complexity and efficient estimators , 2012, 1205.2300.

[20]  Joel A. Tropp,et al.  User-Friendly Tail Bounds for Sums of Random Matrices , 2010, Found. Comput. Math..

[21]  Vincent Nesme,et al.  Note on sampling without replacing from a finite collection of matrices , 2010, ArXiv.

[22]  M. Talagrand,et al.  Probability in Banach Spaces: Isoperimetry and Processes , 1991 .

[23]  Emmanuel J. Candès,et al.  The Power of Convex Relaxation: Near-Optimal Matrix Completion , 2009, IEEE Transactions on Information Theory.

[24]  Martin J. Wainwright,et al.  Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$ -Constrained Quadratic Programming (Lasso) , 2009, IEEE Transactions on Information Theory.