Noisy low-rank matrix completion with general sampling distribution

In the present paper we consider the problem of matrix completion with noise for general sampling schemes. Unlike previous works, in our construction we do not need to know or to evaluate the sampling distribution or the variance of the noise. We propose new nuclear-norm penalized estimators, one of them of the "square-root" type. We prove that, up to a logarithmic factor, our estimators achieve optimal rates with respect to the estimation error

[1]  Rudolf Ahlswede,et al.  Strong converse for identification via quantum channels , 2000, IEEE Trans. Inf. Theory.

[2]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

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

[4]  Andrea Montanari,et al.  Matrix completion from a few entries , 2009, ISIT.

[5]  A. Belloni,et al.  Square-Root Lasso: Pivotal Recovery of Sparse Signals via Conic Programming , 2010, 1009.5689.

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

[7]  V. Koltchinskii.  Von Neumann Entropy Penalization and Low Rank Matrix Estimation , 2010, 1009.2439.

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

[9]  G. Lecu'e,et al.  Sharp oracle inequalities for the prediction of a high-dimensional matrix , 2010, 1008.4886.

[10]  Martin J. Wainwright,et al.  Estimation of (near) low-rank matrices with noise and high-dimensional scaling , 2009, ICML.

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

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

[13]  Ruslan Salakhutdinov,et al.  Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm , 2010, NIPS.

[14]  Ohad Shamir,et al.  Learning with the weighted trace-norm under arbitrary sampling distributions , 2011, NIPS.

[15]  O. Klopp.  Rank penalized estimators for high-dimensional matrices , 2011, 1104.1244.

[16]  Karim Lounici.  Optimal spectral norm rates for noisy low-rank matrix completion , 2011, 1110.5346.

[17]  V. Koltchinskii,et al.  Oracle inequalities in empirical risk minimization and sparse recovery problems , 2011 .

[18]  Nathan Srebro,et al.  Concentration-Based Guarantees for Low-Rank Matrix Reconstruction , 2011, COLT.

[19]  M. Wegkamp,et al.  Optimal selection of reduced rank estimators of high-dimensional matrices , 2010, 1004.2995.

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

[21]  Stéphane Gaïffas,et al.  Sharp Oracle Inequalities for High-Dimensional Matrix Prediction , 2011, IEEE Transactions on Information Theory.

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

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

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

[25]  V. Koltchinskii.  A remark on low rank matrix recovery and noncommutative Bernstein type inequalities , 2013 .

[26]  松井 秀俊.  Statistics for High-Dimensional Data: Methods, Theory and Applications, Peter Buhlman and Sara van de Geer著, Springer, 2011年6月, 558pp., 価格 114,99〓, ISBN 978-3642201912 , 2014 .

[27]  秀俊 松井,et al.  Statistics for High-Dimensional Data: Methods, Theory and Applications , 2014 .