Low-rank matrix recovery via iteratively reweighted least squares minimization

SIAM Journal on Optimization

Volumn 21, Issue 4, 2011, Pages 1614-1640

  Fornasier, Massimo ^a   Rauhut, Holger ^b   Ward, Rachel ^c  

^a JOHANN RADON INSTITUTE FOR COMPUTATIONAL AND APPLIED MATHEMATICS   (Austria)

^b UNIVERSITY OF BONN   (Germany)

^c NEW YORK UNIVERSITY   (United States)

Author keywords

Iteratively reweighted least squares; Low rank matrix recovery; Matrix completion

Indexed keywords

COMPRESSED SENSING; EFFICIENT IMPLEMENTATION; ITERATIVELY REWEIGHTED LEAST SQUARES; LEAST SQUARES PROBLEMS; LINEAR MEASUREMENTS; LOW-RANK MATRICES; MATRIX; MATRIX COMPLETION; MATRIX COMPLETION PROBLEMS; NULL SPACE; NUMERICAL EXPERIMENTS;

APPROXIMATION ALGORITHMS; COMPETITION; ITERATIVE METHODS; LEAST SQUARES APPROXIMATIONS; RECOVERY;

MATRIX ALGEBRA;

EID: 84856046837     PISSN: 10526234     EISSN: None     Source Type: Journal    
DOI: 10.1137/100811404     Document Type: Article

References (36)

1. N. Ailon and E. Liberty, An almost optimal unrestricted fast Johnson-Lindenstrauss transform, in Proceedings of the Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms, D. Randall, ed., SIAM, Philadelphia, ACM, New York, 2011, pp. 185-191.
2. S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge University Press, Cambridge, UK, 2004.
3. J.-F. Cai, E. J. Candès, and Z. Shen, A singular value thresholding algorithm for matrix completion, SIAM J. Optim., 20 (2010), pp. 1956-1982.
4. E. Candès and Y. Plan, Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements, IEEE Trans. Inform. Theory, 57 (2011), pp. 2342-2359.
5. E. J. Candès and B. Recht, Exact matrix completion via convex optimization, Found. Comput. Math., 9 (2009), pp. 717-772.
6. E. J. Candès and T. Tao, The power of convex relaxation: Near-optimal matrix completion, IEEE Trans. Inform. Theory, 56 (2010), pp. 2053-2080.
7. A. Chambolle and P.-L. Lions, Image recovery via total variation minimization and related problems, Numer. Math., 76 (1997), pp. 167-188.
8. A. Cohen, W. Dahmen, and R. A. DeVore, Compressed sensing and best k-term approximation, J. Amer. Math. Soc., 22 (2009), pp. 211-231.
9. I. Daubechies, R. A. DeVore, M. Fornasier, and C. S. Güntürk, Iteratively re-weighted least squares minimization for sparse recovery, Comm. Pure Appl. Math., 63 (2010), pp. 1-38.
10. M. Fazel, Matrix Rank Minimization with Applications, Ph.D. thesis, Stanford University, Stanford, CA, 2002.
11. M. Fornasier and H. Rauhut, Compressive sensing, in Handbook of Mathematical Methods in Imaging, O. Scherzer, ed., Springer, Berlin, New York, 2011, pp. 187-228.
12. 1- minimization, Appl. Comput. Harmon. Anal., 29 (2010), pp. 97-103.
13. q-minimization for 0 < q ≤ 1, Appl. Comput. Harmon. Anal., 26 (2009), pp. 395-407.
14. D. Goldfarb and S. Ma, Convergence of fixed point continuation algorithms for matrix rank minimization, Found. Comput. Math., 11 (2011), pp. 183-210.
15. R. Gribonval and M. Nielsen, Sparse representations in unions of bases, IEEE Trans. Inform. Theory, 49 (2003), pp. 3320-3325.
16. D. Gross, Recovering low-rank matrices from few coefficients in any basis, IEEE Trans. Inform. Theory, 57 (2011), pp. 1548-1566.
17. D. Gross, Y.-K. Liu, S. T. Flammia, S. Becker, and J. Eisert, Quantum state tomography via compressed sensing, Phys. Rev. Lett., 105 (2010), 150401.
18. R. H. Keshavan, A. Montanari, and S. Oh, Matrix completion from a few entries, IEEE Trans. Inform. Theory, 56 (2010), pp. 2980-2998.
19. R. H. Keshavan, A. Montanari, and S. Oh, Matrix completion from noisy entries, J. Machine Learning Res., 11 (2010), pp. 2057-2078.
20. F. Krahmer and R. Ward, New and improved Johnson-Lindenstrauss embeddings via the restricted isometry property, SIAM J. Math. Anal., 43 (2011), pp. 1269-1281.
21. K. Lee and Y. Bresler, ADMiRA: Atomic decomposition for minimum rank approximation, IEEE Trans. Inform. Theory, 56 (2010), pp. 4402-4416.
22. A. S. Lewis and H. S. Sendov, Nonsmooth analysis of singular values. I: Theory, Set-Valued Anal., 13 (2005), pp. 213-241. (Pubitemid 40965854)
23. 2k, Appl. Comput. Harmon. Anal. 31 (2011), pp. 460-468.
24. K. Mohan and M. Fazel, Iterative reweighted least squares for matrix rank minimization, in Proceedings of the 48th Allerton Conference on Communication Control and Computing, IEEE Press, Piscataway, NJ, 2010, pp. 653-661.
25. K. Mohan and M. Fazel, Reweighted nuclear norm minimization with application to system identification, in Proceedings of the American Control Conference, IEEE Press, Piscataway, NJ, 2010, pp. 2953-2959.
26. B. K. Natarajan, Sparse approximate solutions to linear systems, SIAM J. Comput., 24 (1995), pp. 227-234.
27. S. Oymak, K. Mohan, M. Fazel, and B. Hassibi, A Simplified Approach to Recovery Conditions for Low-rank Matrices, preprint, arxiv:1103.1178v2 (2011).
28. A. M. Pinkus, On L1-Approximation, Cambridge Tracts in Math. 93, Cambridge University Press, Cambridge, UK, 1989.
29. A. M. Pinkus, Sparse representations and approximation theory, J. Approx. Theory, 163 (2011), pp. 388-412.
30. H. Rauhut, Compressive sensing and structured random matrices, in Theoretical Foundations and Numerical Methods for Sparse Recovery, M. Fornasier, ed., Radon Series Comp. Appl. Math., deGruyter, Berlin, 2010, pp. 1-92
31. B. Recht, A simpler approach to matrix completion, J. Machine Learning Res., to appear.
32. B. Recht, M. Fazel, and P. A. Parillo, Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization, SIAM Rev., 52 (2010), pp. 471-501.
33. B. Recht, B. Hassibi, and W. Xu, Null space conditions and thresholds for rank minimization, Math. Program. Ser B, 127 (2011), pp. 175-211.
34. R. Ward, Compressed sensing with cross validation, IEEE Trans. Inform. Theory, 55 (2009), pp. 5773-5782.
35. H. Weyl, Das asymptotische Verteilungsgesetz der Eigenwerte linearer partieller Differentialgleichungen (mit einer Anwendung auf die Theorie der Hohlraumstrahlung), Math. Ann., 71 (1912), pp. 441-479.
36. M. A. Woodbury, Inverting Modified Matrices, Technical report 42, Statistical Research Group, Princeton University, Princeton, NJ, 1950.