Normalized iterative hard thresholding for matrix completion

SIAM Journal on Scientific Computing

Volumn 35, Issue 5, 2013, Pages

  Tanner, Jared ^a   Wei, Ke ^a  

^a MAXWELL INSTITUTE FOR MATHEMATICAL SCIENCES   (United Kingdom)

Author keywords

Alternating projection; Compressed sensing; Low rank approximation; Matrix completion

Indexed keywords

APPROXIMATION THEORY; COMPRESSED SENSING; ITERATIVE METHODS; RECOVERY;

ALTERNATING PROJECTION ALGORITHM; ALTERNATING PROJECTIONS; AVERAGE CASE PERFORMANCE; COMPUTATIONALLY EFFICIENT; ITERATIVE HARD THRESHOLDING; LIMITED INFORMATION; LOW RANK APPROXIMATIONS; MATRIX COMPLETION;

MATRIX ALGEBRA;

EID: 84886858077     PISSN: 10648275     EISSN: 10957200     Source Type: Journal    
DOI: 10.1137/120876459     Document Type: Conference Paper

References (45)

1. J. D. Blanchard, C. Cartis, and J. Tanner, Compressed sensing: How sharp is the restricted isometry property?, SIAM Rev., 53 (2011), pp. 105-125.
2. T. Blumensath and M. E. Davies, Iterative hard thresholding for compressed sensing, Appl. Comput. Harmon. Anal., 27 (2009), pp. 265-274.
3. T. Blumensath and M. E. Davies, Normalized iterative hard thresholding: Guaranteed stability and performance, IEEE J. Selected Topics Signal Process., 4 (2010), pp. 298-309.
4. A. M. Bruckstein, D. L. Donoho, and M. Elad, From sparse solutions of systems of equations to sparse modeling of signals and images, SIAM Rev., 51 (2009), pp. 34-81.
5. J.-F. Cai, E. J. Candes, and Z. Sun, A singular value thresholding algorithm for matrix completion, SIAM J. Optim., 20 (2010), pp. 1956-1982.
6. J. F. Cai and S. Osher, Fast Singular Value Thresholding without Singular Value Decomposition, Tech. report, Rice University, Houston, TX, 2010.
7. E. J. Candes, Compressive sampling, in Proceedings of the International Congress of Mathematics, Madrid, Spain, 2006, pp. 1433-1452.
8. E. J. Candes, The restricted isometry property and its implications for compressed sensing, C.R. Math. Acad. Sci. Paris, 346 (2008), pp. 589-592.
9. E. J. Candes and B. Recht, Exact matrix completion via convex optimization, Found. Comput. Math., 9 (2009), pp. 717-772.
10. E. J. Candes, J. K. Romberg, and T. Tao, Stable signal recovery from incomplete and inaccurate measurements, Comm. Pure Appl. Math., 59 (2006), pp. 1207-1223. (Pubitemid 43988295)
11. E. J. Candes and T. Tao, Decoding by linear programming, IEEE Trans. Inform. Theory, 51 (2005), pp. 4203-4215. (Pubitemid 41800353)
12. E. J. Candes and T. Tao, The power of convex relaxation: Near-optimal matrix completion, IEEE Trans. Inform. Theory, 56 (2009), pp. 2053-1080.
13. A. Cohen, W. Dahmen, and R. De Vore, Compressed sensing and best k-term approximation, J. Amer. Math. Soc., 22 (2009), pp. 211-231.
14. W. Dai and O. Milenkovic, Subspace pursuit for compressive sensing signal reconstruction, IEEE Trans. Inform. Theory, 55 (2009), pp. 2230-2249.
15. W. Dai, O. Milenkovic, and E. Kerman, Subspace evolution and transfer (SET) for low-rank matrix completion, IEEE Trans. Signal Process., 59 (2011), pp. 3120-3132.
16. D. L. Donoho, Compressed sensing, IEEE Trans. Inform. Theory, 52 (2006), pp. 1289-1306.
17. D. L. Donoho, Neighborliness Polytopes and Sparse Solution of Underdetermined Linear Equations, Tech. report, Stanford University, Stanford, CA, 2006.
18. D. L. Donoho and J. Tanner, Precise undersampling theorems, Proc. IEEE, 98 (2010), pp. 913-924.
19. Y. C. Eldar, D. Needell, and Y. Plan, Unicity conditions for low-rank matrix recovery, Appl. Comput. Harmon. Anal., 33 (2012), pp. 309-314.
20. S. Foucart, Hard thresholding pursuit: An algorithm for compressive sensing, SIAM J. Numer. Anal., 49 (2011), pp. 2543-2563.
21. D. Goldfarb and S. Ma, Convergence of fixed-point continuation algorithms for matrix rank minimization, Found. Comput. Math., 11 (2011), pp. 183-210.
22. J. P. Haldar and D. Hernando, Rank-constrained solutions to linear matrix equations using power-factorization, IEEE Trans. Signal Process. Lett., 16 (2009), pp. 584-587.
23. N. J. A. Harvey, D. R. Karger, and S. Yekhanin, The complexity of matrix completion, in Proceedings of the 17th Annual ACM-SIAM Symposium on Discrete Algorithms, ACM, New York, SIAM, Philadelphia, 2006, pp. 1103-1111. (Pubitemid 43275337)
24. P. Jain, R. Meka, and I. Dhillon, Guaranteed rank minimization via singular value projection, in Proceedings of the Neural Information Processing Systems Conference (NIPS), Vancouver, Canada, 2010, pp. 937-945.
25. R. H. Keshavan, A. Montanari, and S. Oh, Matrix completion from a few entries, IEEE Trans. Inform. Theory, 56 (2010), pp. 2980-2998.
26. R. H. Keshavan and S. Oh, Optspace: A gradient descent algorithm on the Grassmann manifold for matrix completion, http://arxiv.org/abs/0910.5260v2 2009.
27. A. Kyrillidis and V. Cevher, Matrix ALPS: Accelerated low rank and sparse matrix reconstruction, in Proceedings of the 2012 IEEE Statistical Signal Processing Workshop, IEEE, New York, 2012, pp. 185-188.
28. A. Kyrillidis and V. Cevher, Matrix recipes for hard thresholding methods, J. Math. Imaging Vision, April (2013), DOI: 10.1007/s10851-013-0434-7.
29. R. M. Larsen, PROPACK available online from http://sun.stanford.edu/ rmunk/PROPACK/.
30. K. Lee and Y. Bresler, ADMiRA: Atomic decomposition for minimum rank approximation, IEEE Trans. Inform. Theory, 56 (2010), pp. 4402-4416.
31. A. S. Lewis and J. Malick, Alternating projections on manifolds, Math. Oper. Res., 33 (2008), pp. 216-234.
32. Z. Lin, M. Chen, and Y. Ma, The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices, http://arxiv.org/abs/1009.5055 2010.
33. S. Ma, D. Goldfarb, and L. Chen, Fixed point and Bregman iterative methods for matrix rank minimization, Math. Program. Ser. A, 128 (2011), pp. 321-353.
34. A. Maleki and D. L. Donoho, Optimally tuned iterative reconstruction algorithms for compressed sensing, IEEE J. Selected Topics Signal Process., 4 (2010), pp. 330-341.
35. G. Meyer, S. Bonnabel, and R. Sepulchre, Linear regression under fixed-rank constraints: A Riemannian approach, in Proceedings of the 28th ACM International Conference on Machine Learning (ICML2011) (Bellevue, Washington), ACM, New York, 2011, pp. 545- 552.
36. M. Michenkova, Numerical Algorithms for Low-Rank Matrix Completion Problems, Tech. report, ETH, Switzerland, http://www.math.ethz.ch/kressner/ students/michenkova.pdf 2011.
37. D. Needell and J. Tropp, Cosamp: Iterative signal recovery from incomplete and inaccurate samples, Appl. Comput. Harmon. Anal., 26 (2009), pp. 301-321.
38. B. Recht, M. Fazel, and P. A. Parrilo, Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization, SIAM Rev., 52 (2010), pp. 471-501.
39. B. Recht, W. Xu, and B. Hassibi, Null space conditions and thresholds for rank minimization, Math. Program. Ser. B, (2011), pp. 175-211.
40. U. Shalit, D. Weinshall, and G. Chechik, Online learning in the manifold of low-rank matrices, Adv. Neural Inform. Process. Syst., 23 (2010), p. 2128-2136.
41. K. Toh and S. Yun, An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems, Pacific J. Optim., 16 (2010), pp. 615-640.
42. K. C. Toh, M. J. Todd, and R. H. Tutuncu, SDPT3 4.0(beta) http://www.math.nus.edu.sg/mattohkc/sdpt3.html, 2006.
43. B. Van de reycken, Low rank matrix completion by Riemannian optimization, SIAM J. Optim., to appear.
44. B. Van de reycken and S. Van de walle, A Riemannian optimization approach for computing low-rank solutions of Lyapunov equations, SIAM J. Matrix Anal. Appl., 31 (2010), pp. 2553-2579.
45. Z. Wen, W. Yin, and Y. Zhang, Solving a low-rank factorization model for matrix completion by a non-linear successive over-relaxation algorithm, Math. Program. Comput., 4 (2012), pp. 333-361.