Matrix Completion from $O(n)$ Samples in Linear Time

We consider the problem of reconstructing a rank-$k$ $n \times n$ matrix $M$ from a sampling of its entries. Under a certain incoherence assumption on $M$ and for the case when both the rank and the condition number of $M$ are bounded, it was shown in \cite{CandesRecht2009, CandesTao2010, keshavan2010, Recht2011, Jain2012, Hardt2014} that $M$ can be recovered exactly or approximately (depending on some trade-off between accuracy and computational complexity) using $O(n \, \text{poly}(\log n))$ samples in super-linear time $O(n^{a} \, \text{poly}(\log n))$ for some constant $a \geq 1$. In this paper, we propose a new matrix completion algorithm using a novel sampling scheme based on a union of independent sparse random regular bipartite graphs. We show that under the same conditions w.h.p. our algorithm recovers an $\epsilon$-approximation of $M$ in terms of the Frobenius norm using $O(n \log^2(1/\epsilon))$ samples and in linear time $O(n \log^2(1/\epsilon))$. This provides the best known bounds both on the sample complexity and computational complexity for reconstructing (approximately) an unknown low-rank matrix. The novelty of our algorithm is two new steps of thresholding singular values and rescaling singular vectors in the application of the "vanilla" alternating minimization algorithm. The structure of sparse random regular graphs is used heavily for controlling the impact of these regularization steps.

[1]  David P. Woodruff,et al.  Optimal Sample Complexity for Matrix Completion and Related Problems via 𝓁s2-Regularization , 2017, ArXiv.

[2]  Nicholas A. Cook Discrepancy properties for random regular digraphs , 2014, Random Struct. Algorithms.

[3]  John D. Lafferty,et al.  Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent , 2016, ArXiv.

[4]  Zhaoran Wang,et al.  A Nonconvex Optimization Framework for Low Rank Matrix Estimation , 2015, NIPS.

[5]  Nigel Boston,et al.  A characterization of deterministic sampling patterns for low-rank matrix completion , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[6]  Joel A. Tropp,et al.  An Introduction to Matrix Concentration Inequalities , 2015, Found. Trends Mach. Learn..

[7]  Zhi-Quan Luo,et al.  Guaranteed Matrix Completion via Non-Convex Factorization , 2014, IEEE Transactions on Information Theory.

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

[9]  Doron Puder,et al.  Expansion of random graphs: new proofs, new results , 2012, 1212.5216.

[10]  Franz J. Király,et al.  The algebraic combinatorial approach for low-rank matrix completion , 2012, J. Mach. Learn. Res..

[11]  Prateek Jain,et al.  Universal Matrix Completion , 2014, ICML.

[12]  Moritz Hardt,et al.  Understanding Alternating Minimization for Matrix Completion , 2013, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

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

[14]  M. Moslehian Ky Fan inequalities , 2011, 1108.1467.

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

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

[17]  TibshiraniRobert,et al.  Spectral Regularization Algorithms for Learning Large Incomplete Matrices , 2010 .

[18]  Robert Tibshirani,et al.  Spectral Regularization Algorithms for Learning Large Incomplete Matrices , 2010, J. Mach. Learn. Res..

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

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

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

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

[23]  N. Wormald Models of random regular graphs , 2010 .

[24]  Inderjit S. Dhillon,et al.  Matrix Completion from Power-Law Distributed Samples , 2009, NIPS.

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

[26]  Amin Saberi,et al.  A Sequential Algorithm for Generating Random Graphs , 2007, Algorithmica.

[27]  B. Z. Moroz,et al.  london mathematical society lecture note series , 2007 .

[28]  Jeong Han Kim,et al.  Poisson Cloning Model for Random Graphs , 2008, 0805.4133.

[29]  Alan M. Frieze,et al.  Random graphs , 2006, SODA '06.

[30]  E. Lesigne,et al.  Heads or tails , 2005 .

[31]  N. Wormald Surveys in Combinatorics, 1999: Models of Random Regular Graphs , 1999 .

[32]  Béla Bollobás,et al.  Random Graphs , 1985 .

[33]  G. Golub Matrix computations , 1983 .