MC^2: A Two-Phase Algorithm for Leveraged Matrix Completion

Leverage scores, loosely speaking, reflect the importance of the rows and columns of a matrix. Ideally, given the leverage scores of a rank-$r$ matrix $M\in\mathbb{R}^{n\times n}$, that matrix can be reliably completed from just $O(rn\log^{2}n)$ samples if the samples are chosen randomly from a nonuniform distribution induced by the leverage scores. In practice, however, the leverage scores are often unknown a priori. As such, the sample complexity in uniform matrix completion---using uniform random sampling---increases to $O(\eta(M)\cdot rn\log^{2}n)$, where $\eta(M)$ is the largest leverage score of $M$. In this paper, we propose a two-phase algorithm called MC$^2$ for matrix completion: in the first phase, the leverage scores are estimated based on uniform random samples, and then in the second phase the matrix is resampled nonuniformly based on the estimated leverage scores and then completed. For well-conditioned matrices, the total sample complexity of MC$^2$ is no worse than uniform matrix completion, and for certain classes of well-conditioned matrices---namely, reasonably coherent matrices whose leverage scores exhibit mild decay---MC$^2$ requires substantially fewer samples. Numerical simulations suggest that the algorithm outperforms uniform matrix completion in a broad class of matrices, and in particular, is much less sensitive to the condition number than our theory currently requires.

[1]  Ilse C. F. Ipsen,et al.  Conditioning of Leverage Scores and Computation by QR Decomposition , 2015, SIAM J. Matrix Anal. Appl..

[2]  Benjamin Recht,et al.  A Simpler Approach to Matrix Completion , 2009, J. Mach. Learn. Res..

[3]  David P. Woodruff,et al.  Fast approximation of matrix coherence and statistical leverage , 2011, ICML.

[4]  Robert D. Nowak,et al.  High-Rank Matrix Completion , 2012, AISTATS.

[5]  Andrea Montanari,et al.  Matrix Completion from Noisy Entries , 2009, J. Mach. Learn. Res..

[6]  Monique Laurent,et al.  Matrix Completion Problems , 2009, Encyclopedia of Optimization.

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

[8]  Massimo Fornasier,et al.  Low-rank Matrix Recovery via Iteratively Reweighted Least Squares Minimization , 2010, SIAM J. Optim..

[9]  Cun-Hui Zhang,et al.  A graphical approach to the analysis of matrix completion , 2016 .

[10]  Richard Peng,et al.  Uniform Sampling for Matrix Approximation , 2014, ITCS.

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

[12]  Sujay Sanghavi,et al.  A New Sampling Technique for Tensors , 2015, ArXiv.

[13]  Andrea Montanari,et al.  Matrix completion from a few entries , 2009, 2009 IEEE International Symposium on Information Theory.

[14]  Michael W. Mahoney,et al.  Low-distortion subspace embeddings in input-sparsity time and applications to robust linear regression , 2012, STOC '13.

[15]  Yudong Chen,et al.  Incoherence-Optimal Matrix Completion , 2013, IEEE Transactions on Information Theory.

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

[17]  Prateek Jain,et al.  Low-rank matrix completion using alternating minimization , 2012, STOC '13.

[18]  Mary Wootters,et al.  Fast matrix completion without the condition number , 2014, COLT.

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

[20]  Ameet Talwalkar,et al.  Can matrix coherence be efficiently and accurately estimated? , 2011, AISTATS.

[21]  Sujay Sanghavi,et al.  Completing any low-rank matrix, provably , 2013, J. Mach. Learn. Res..

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

[23]  Ewout van den Berg,et al.  1-Bit Matrix Completion , 2012, ArXiv.

[24]  Dimitris Papailiopoulos,et al.  Provable deterministic leverage score sampling , 2014, KDD.

[25]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[26]  Nathan Halko,et al.  Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions , 2009, SIAM Rev..