Iterative hard thresholding for low-rank recovery from rank-one projections

A novel algorithm for the recovery of low-rank matrices acquired via compressive linear measurements is proposed and analyzed. The algorithm, a variation on the iterative hard thresholding algorithm for low-rank recovery, is designed to succeed in situations where the standard rank-restricted isometry property fails, e.g. in case of subexponential unstructured measurements or of subgaussian rank-one measurements. The stability and robustness of the algorithm are established based on distinctive matrix-analytic ingredients and its performance is substantiated numerically.

[1]  Simon Foucart,et al.  Recovering low-rank matrices from binary measurements , 2019, Inverse Problems & Imaging.

[2]  Shiqian Ma,et al.  Convergence of Fixed-Point Continuation Algorithms for Matrix Rank Minimization , 2009, Found. Comput. Math..

[3]  Jared Tanner,et al.  Normalized Iterative Hard Thresholding for Matrix Completion , 2013, SIAM J. Sci. Comput..

[4]  Donald Goldfarband Shiqian CONVERGENCE OF FIXED POINT CONTINUATION ALGORITHMS FOR MATRIX RANK MINIMIZATION , 2010 .

[5]  Inderjit S. Dhillon,et al.  Guaranteed Rank Minimization via Singular Value Projection , 2009, NIPS.

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

[7]  Piotr Indyk,et al.  Approximation Algorithms for Model-Based Compressive Sensing , 2014, IEEE Transactions on Information Theory.

[8]  Ping Li,et al.  A Tight Bound of Hard Thresholding , 2016, J. Mach. Learn. Res..

[9]  Ming-Jun Lai,et al.  Sparse recovery with pre-Gaussian random matrices , 2010 .

[10]  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.

[11]  Guillaume Lecué,et al.  An IHT Algorithm for Sparse Recovery From Subexponential Measurements , 2017, IEEE Signal Processing Letters.

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

[13]  Yuxin Chen,et al.  Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems , 2015, NIPS.

[14]  Anru Zhang,et al.  ROP: Matrix Recovery via Rank-One Projections , 2013, ArXiv.