A max-norm constrained minimization approach to 1-bit matrix completion

Journal of Machine Learning Research

Volumn 14, Issue , 2013, Pages 3619-3647

  Cai, Tony ^a   Zhou, Wen Xin ^b  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

^b UNIVERSITY OF MELBOURNE   (Australia)

Author keywords

1 bit matrix completion; Constrained optimization; Low rank matrix; Max norm; Maximum likelihood estimate; Optimal rate of convergence; Trace norm

Indexed keywords

LOW-RANK MATRICES; MATRIX COMPLETION; MAX-NORM; MAXIMUM LIKELIHOOD ESTIMATE; OPTIMAL RATE OF CONVERGENCE; TRACE-NORM;

CONSTRAINED OPTIMIZATION; MAXIMUM LIKELIHOOD ESTIMATION; RELAXATION PROCESSES;

APPROXIMATION THEORY;

EID: 84893492266     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (36)

1. A. Ai, A. Lapanowski, Y. Plan and R. Vershynin. One-bit compressed sensing with non-Gaussian measurements. Linear Algebra and Its Applications, forthcoming, 2013.
2. P. Bartlett and S. Mendelson. Rademacher and Gaussian complexities: risk bounds and structural results. Journal of Machine Learning Research, 3:463-482, 2002.
3. P. Biswas, T. C. Lian, T. C.Wang and Y. Ye. Semidefinite programming based algorithms for sensor network localization. ACM Transactions on Sensor Networks, 2(2):188-220, 2006. (Pubitemid 44188494)
4. P. Boufounos and R. G. Baraniuk. 1-bit compressive sensing. In Proceedings of the 42nd Annual Conference on Information Sciences and Systems, pages 16-21, Princeton, NJ, March 2008.
5. S. Burer and R. D. C. Monteiro. A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization. Mathematical Programming, Series B, 95(2):329-357, February 2003. (Pubitemid 44757858)
6. T. T. Cai andW.-X. Zhou Matrix completion via max-norm constrained optimization. arXiv preprint arXiv: 1303.0341, 2013.
7. T. M. Cover and J. A. Thomas. Elements of Information Theory. John Wiley and Sons, New York, 1991.
8. M. A. Davenport, Y. Plan, E. van den Berg andM.Wooters. 1-bit matrix completion. arXiv preprint arXiv:1209.3672, 2012.
9. R. Foygel, R. Salakhuidinov, O. Shamir and N. Srebro. Learning with the weighted trace-norm under arbitrary sampling distributions. Advances in Neural Information Processing Systems (NIPS), 24, pages 2133-2141, 2011.
10. R. Foygel and N. Srebro. Concentration-based guarantees for low-rank matrix reconstruction. JMLR: Workshop and Conference Proceedings, 19:315-339, 2011.
11. D. Goldberg, D. Nichols, B. M. Oki and D. Terry. Using collaborative filtering to weave an information tapestry. Communications of the ACM, 35(12):61-70, December 1992.
12. P. E. Green and Y.Wind. Multiattribute Decisions in Marketing: A Measurement Approach. Dryden Press, Hinsdale, IL, 1973.
13. D. Gross and V. Nesme. Note on sampling without replacing from a finite collection of matrices. arXiv preprint arXiv:1001.2738, 2010.
14. L. Jacques, J. N. Laska, P. T. Boufounos and R. G. Baraniuk. Robust 1-bit compressive sensing via binary stable embeddings of sparse vectors. arXiv preprint arXiv:1104.3160, 2011.
15. M. Jaggi. Revisiting Frank-Wolfe: projection-free sparse convex optimization. JMLR: Workshop and Conference Proceedings, 28(1):427-435, 2013.
16. G. J. O. Jameson. Summing and Nuclear Norms in Banach Space Theory. London Mathematical Society Student Texts, 8. Cambridge University Press, Cambridge, 1987.
17. K. Joag-Dev and F. Proschan. Negative association of random variables with applications. Annals of Statistics, 11(1):286-295, 1983.
18. O. Klopp. Noisy low-rank matrix completion with general sampling distribution. Bernoulli, forthcoming, 2012.
19. V. Koltchinskii, K. Lounici and A. B. Tsybakov. Nuclear norm penalization and optimal rates for noisy low rank matrix completion. Annals of Statistics, 39(5):2302-2329, 2011.
20. J. N. Laska and R. G. Baraniuk. Regime change: bit-depth versus measurement-rate in compressive sensing. IEEE Transactions on Signal Processing, 60(7):3496-3505, 2012.
21. R. Latala. Some estimates of norms of random matrices. Proceedings of the AmericanMathematical Society, 133(5):1273-1282, 2005. (Pubitemid 40622652)
22. M. Ledoux andM. Talagrand. Probability in Banach Spaces. Isoperimetry and Processes. Springer-Verlag, Berlin, 2011.
23. J. Lee, B. Recht, R. Salakhutdinov, N. Srebro and J. Tropp. Practical large-scale optimization for max-norm regularization. Advances in Neural Information Processing Systems (NIPS), 23, 2010.
24. N. Linial, S.Mendelson, G. Schechtman and A. Shraibman. Complexity measures of sign measures. Combinatorica, 27(4):439-463, 2007.
25. S. Negahban and M. J. Wainwright. Restricted strong convexity and weighted matrix completion: optimal bounds with noise. Journal of Machine Learning Research, 13:1665-1697, 2012.
26. Y. Plan and R. Vershynin. Robust 1-bit compressed sensing and sparse logistic regression: a convex programming approach. IEEE Transactions on Information Theory, 59(1):482-494, January, 2013a.
27. Y. Plan and R. Vershynin. One-bit compressed sensing by linear programming. Communications on Pure and Applied Mathematics, 66(8):1275-1297, August, 2013b.
28. R. Salakhutdinov and N. Srebro. Collaborative filtering in a non-uniform world: learning with the weighted trace norm. Advances in Neural Information Processing Systems (NIPS), 23, December, 2010.
29. Y. Seginer. The expected norm of random matrices. Combinatorics, Probability and Computing, 9(2):149-166, March, 2000.
30. I. Spence and D. W. Domoney. Single subject incomplete designs for nonmetric multidimensional scaling. Psychometrika, 39(4):469-490, December, 1974.
31. N. Srebro, J. Rennie and T. Jaakkola. Maximum-margin matrix factorization. Advances in Neural Information Processing Systems (NIPS), 17, pages 1329-1336. MIT Press, 2005.
32. N. Srebro and A. Shraibman. Rank, trace-norm and max-norm. In Learning theory, Proceedings of COLT-2005. Lecture Notes in Computer Science, 3559:545-560, Springer, Berlin, 2005.
33. N. Srebro, K. Sridharan and A. Tewari. Optimistic rates for learning with a smooth loss. arXiv preprint arXiv:1009.3896, 2010.
34. J. A. Tropp. User-friendly tail bounds for sums of random matrices. Foundations of Computational Mathematics, 12(4):389-434, August, 2012.
35. Y. Yang and A. Barron. Information-theoretic determination of minimax rates of convergence. Annals of Statistics, 27(5):1564-1599, 1999.
36. B. Yu. Assouad, Fano and Le Cam. Research Papers in Probability and Statistics: Festschrift for Lucien Le Cam, pages 423-435.