Tight recovery thresholds and robustness analysis for nuclear norm minimization

Nuclear norm minimization (NNM) has recently gained significant attention for its use in rank minimization problems. Using null space characterizations, recovery thresholds for NNM have been previously studied for the case of Gaussian measurements as matrix dimensions tend to infinity. However simulations show that the thresholds are far from optimal, especially in the low rank region. In this paper we apply the recent analysis of Stojnic for ℓ1-minimization to the null space conditions of NNM. The results are significantly better and in particular our weak threshold appears to match with simulation results. Further, our closed form bounds suggest for any rank growing linearly with matrix size n one needs only three times of oversampling (the model complexity) for weak recovery and eight times for strong recovery. Additionally, the results for robustness analysis are given which indicate with slightly more measurements recovery guarantees for approximately low rank matrices can be given.

[1]  J. Kuelbs.  Probability on Banach spaces , 1978 .

[2]  Emmanuel J. Candès,et al.  Matrix Completion With Noise , 2009, Proceedings of the IEEE.

[3]  Babak Hassibi,et al.  Improved thresholds for rank minimization , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  M. Stojnic.  Various thresholds for $\ell_1$-optimization in compressed sensing , 2009 .

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

[6]  Stephen P. Boyd,et al.  Log-det heuristic for matrix rank minimization with applications to Hankel and Euclidean distance matrices , 2003, Proceedings of the 2003 American Control Conference, 2003..

[7]  Weiyu Xu,et al.  Null space conditions and thresholds for rank minimization , 2011, Math. Program..

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

[9]  Ralf R. Müller,et al.  Random matrices, free probability and the replica method , 2004, EUSIPCO.

[10]  Mihailo Stojnic,et al.  Various thresholds for ℓ1-optimization in compressed sensing , 2009, ArXiv.

[11]  Stephen P. Boyd,et al.  Rank minimization and applications in system theory , 2004, Proceedings of the 2004 American Control Conference.

[12]  M. Stephanov,et al.  Random Matrices , 2005, hep-ph/0509286.

[13]  Mihailo Stojnic,et al.  Block-length dependent thresholds in block-sparse compressed sensing , 2009, ArXiv.

[14]  Emmanuel J. Candès,et al.  Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements , 2010, ArXiv.

[15]  Pablo A. Parrilo,et al.  The Convex Geometry of Linear Inverse Problems , 2010, Foundations of Computational Mathematics.

[16]  D. Donoho,et al.  Thresholds for the Recovery of Sparse Solutions via L1 Minimization , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[17]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[18]  Weiyu Xu,et al.  On sharp performance bounds for robust sparse signal recoveries , 2009, 2009 IEEE International Symposium on Information Theory.

[19]  Babak Hassibi,et al.  New Null Space Results and Recovery Thresholds for Matrix Rank Minimization , 2010, ArXiv.

[20]  L. Mirsky.  A trace inequality of John von Neumann , 1975 .