Near-Optimal Estimation of Simultaneously Sparse and Low-Rank Matrices from Nested Linear Measurements

In this paper we consider the problem of estimating simultaneously low-rank and row-wise sparse matrices from nested linear measurements where the linear operator consists of the product of a linear operator $\mathcal{W}$ and a matrix $\mathbf{\varPsi}$. Leveraging the nested structure of the measurement operator, we propose a computationally efficient two-stage algorithm for estimating the simultaneously structured target matrix. Assuming that $\mathcal{W}$ is a restricted isometry for low-rank matrices and $\mathbf{\varPsi}$ is a restricted isometry for row-wise sparse matrices, we establish an accuracy guarantee that holds uniformly for all sufficiently low-rank and row-wise sparse matrices with high probability. Furthermore, using standard tools from information theory, we establish a minimax lower bound for estimation of simultaneously low-rank and row-wise sparse matrices from linear measurements that need not be nested. The accuracy bounds established for the algorithm, that also serve as a minimax upper bound, differ from the derived minimax lower bound merely by a polylogarithmic factor of the dimensions. Therefore, the proposed algorithm is nearly minimax optimal. We also discuss some applications of the proposed observation model and evaluate our algorithm through numerical simulation.

[1]  Götz E. Pfander,et al.  Sampling Theory, a Renaissance : Compressive Sensing and Other Developments , 2015 .

[2]  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.

[3]  Yonina C. Eldar,et al.  Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices , 2012, IEEE Transactions on Information Theory.

[4]  Prateek Jain,et al.  Phase Retrieval Using Alternating Minimization , 2013, IEEE Transactions on Signal Processing.

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

[6]  P. Massart,et al.  Adaptive estimation of a quadratic functional by model selection , 2000 .

[7]  Joel A. Tropp,et al.  Convex recovery of a structured signal from independent random linear measurements , 2014, ArXiv.

[8]  Xiaodong Li,et al.  Sparse Signal Recovery from Quadratic Measurements via Convex Programming , 2012, SIAM J. Math. Anal..

[9]  T. Cai,et al.  Optimal estimation and rank detection for sparse spiked covariance matrices , 2013, Probability theory and related fields.

[10]  Lei Tian,et al.  Compressive Phase Retrieval , 2011 .

[11]  Holger Boche,et al.  Fast compressive phase retrieval from Fourier measurements , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Andrea J. Goldsmith,et al.  Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming , 2013, IEEE Transactions on Information Theory.

[13]  Philippe Rigollet,et al.  Complexity Theoretic Lower Bounds for Sparse Principal Component Detection , 2013, COLT.

[14]  Yoram Bresler,et al.  Near Optimal Compressed Sensing of Sparse Rank-One Matrices via Sparse Power Factorization , 2013, ArXiv.

[15]  Xiaodong Li,et al.  Phase Retrieval via Wirtinger Flow: Theory and Algorithms , 2014, IEEE Transactions on Information Theory.

[16]  Michael I. Jordan,et al.  A Direct Formulation for Sparse Pca Using Semidefinite Programming , 2004, SIAM Rev..

[17]  P. Massart,et al.  Concentration inequalities and model selection , 2007 .

[18]  Yonina C. Eldar,et al.  GESPAR: Efficient Phase Retrieval of Sparse Signals , 2013, IEEE Transactions on Signal Processing.

[19]  Emmanuel J. Candès,et al.  Templates for convex cone problems with applications to sparse signal recovery , 2010, Math. Program. Comput..

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

[21]  Allen Y. Yang,et al.  CPRL -- An Extension of Compressive Sensing to the Phase Retrieval Problem , 2012, NIPS.

[22]  Martin J. Wainwright,et al.  Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$ -Balls , 2009, IEEE Transactions on Information Theory.

[23]  Holger Rauhut,et al.  Low rank matrix recovery from rank one measurements , 2014, ArXiv.

[24]  Justin K. Romberg,et al.  Efficient Compressive Phase Retrieval with Constrained Sensing Vectors , 2015, NIPS.

[25]  Justin K. Romberg,et al.  Lifting for Blind Deconvolution in Random Mask Imaging: Identifiability and Convex Relaxation , 2015, SIAM J. Imaging Sci..

[26]  I. Johnstone,et al.  On Consistency and Sparsity for Principal Components Analysis in High Dimensions , 2009, Journal of the American Statistical Association.

[27]  Jing Lei,et al.  Fantope Projection and Selection: A near-optimal convex relaxation of sparse PCA , 2013, NIPS.

[28]  Dan Yang,et al.  Optimal denoising of simultaneously sparse and low rank matrices in high dimensions , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[29]  Yonina C. Eldar,et al.  Sparsity Based Sub-wavelength Imaging with Partially Incoherent Light via Quadratic Compressed Sensing References and Links , 2022 .

[30]  T. Cai,et al.  Sparse PCA: Optimal rates and adaptive estimation , 2012, 1211.1309.

[31]  B. Recht,et al.  Convex Blind Deconvolution with Random Masks , 2014 .

[32]  M. Wainwright,et al.  High-dimensional analysis of semidefinite relaxations for sparse principal components , 2008, 2008 IEEE International Symposium on Information Theory.

[33]  Yonina C. Eldar,et al.  Robust Recovery of Signals From a Structured Union of Subspaces , 2008, IEEE Transactions on Information Theory.

[34]  Zhaoran Wang,et al.  Tighten after Relax: Minimax-Optimal Sparse PCA in Polynomial Time , 2014, NIPS.

[35]  Emmanuel J. Candès,et al.  PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming , 2011, ArXiv.

[36]  Alexandre B. Tsybakov,et al.  Introduction to Nonparametric Estimation , 2008, Springer series in statistics.

[37]  R. DeVore,et al.  A Simple Proof of the Restricted Isometry Property for Random Matrices , 2008 .

[38]  A. Tsybakov,et al.  Estimation of high-dimensional low-rank matrices , 2009, 0912.5338.

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

[40]  Junfeng Yang,et al.  Alternating Direction Algorithms for 1-Problems in Compressive Sensing , 2009, SIAM J. Sci. Comput..

[41]  Justin K. Romberg,et al.  Sketching for simultaneously sparse and low-rank covariance matrices , 2015, 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[42]  Yang Wang,et al.  Robust sparse phase retrieval made easy , 2014, 1410.5295.

[43]  V. Koltchinskii,et al.  Nuclear norm penalization and optimal rates for noisy low rank matrix completion , 2010, 1011.6256.

[44]  Pablo A. Parrilo,et al.  Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

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