Recovery of low-rank matrices under affine constraints via a smoothed rank function

IEEE Transactions on Signal Processing

Volumn 62, Issue 4, 2014, Pages 981-992

  Malek Mohammadi, Mohammadreza ^a   Babaie Zadeh, Massoud ^a   Amini, Arash ^a   Jutten, Christian ^a  

^a SHARIF UNIVERSITY OF TECHNOLOGY   (Iran)

Author keywords

affine rank minimization (ARM); compressive sensing; matrix completion (MC); nuclear norm minimization (NNM); rank approximation; spherical section property (SSP)

Indexed keywords

COMPRESSIVE SENSING; MATRIX COMPLETION; NUCLEAR NORM MINIMIZATIONS; RANK APPROXIMATION; RANK MINIMIZATIONS; SPHERICAL SECTION PROPERTY (SSP);

MATRIX ALGEBRA; OPTIMIZATION; RECOVERY;

APPROXIMATION ALGORITHMS;

EID: 84893431754     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSP.2013.2295557     Document Type: Article

References (43)

1. B. Recht, M. Fazel, and P.A. Parrilo, "Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization," SIAM Rev., vol. 55, pp. 471-501, 2010.
2. E. J. Candés and B. Recht, "Exact matrix completion via convex optimization," Found. Comput. Math., vol. 9, no. 6, pp. 717-772, 2009.
3. B. Recht, W. Xu, and B. Hassibi, "Null space conditions and thresholds for rank minimization," Math. Program., vol. 127, no. 1, pp. 175-202, 2011.
4. E. J. Candés and Y. Plan, "Matrix completion with noise," Proc. IEEE, vol. 98, no. 6, pp. 925-936, 2010.
5. M. Fazel, H. Hindi, and S. Boyd, "A rank minimization heuristic with application to minimum order system approximation," in Proc. Amer. Control Conf., 2001, pp. 4734-4739. (Pubitemid 32837075)
6. Z. Liu and L. Vandenberghe, "Interior-point method for nuclear norm approximation with application to system identification," SIAM. J. Matrix Anal. Appl., vol. 31, no. 3, pp. 1235-1256, 2009.
7. T. Cox and M. A. A. Cox, Multidimensional Scaling. London, U.K.: Chapman & Hall, 1994.
8. Y. Amit, M. Fink, N. Srebro, and S. Ullman, "Uncovering shared structures in multiclass classification," in Proc. 24th Int. Conf. Mach. Learn., 2007, vol. 24, pp. 17-24.
9. D. Gross, Y. K. Liu, S. T. Flammia, S. Becker, and J. Eisert, "Quantum state tomography via compressed sensing," Phys. Rev. Lett., vol. 105, no. 15, pp. 150401-1-150401-4, 2010.
10. J. Meng, W. Yin, H. Li, E. Hossain, and Z. Han, "Collaborative spectrum sensing from sparse observations in cognitive radio networks," IEEE J. Sel. Areas Commun., vol. 29, no. 2, pp. 327-337, 2011.
11. N. Ito, E. Vincent, N. Ono, R. Gribonval, and S. Sagayama, "Crystalmusic: Accurate localization of multiple sources in diffuse noise environments using crystal-shaped microphone arrays," Latent Variable Anal. Signal Separat., vol. 6365, pp. 81-88, 2010.
12. R. O. Schmidt, "Multiple emitter location and signal parameter estimation," IEEE Trans. Antennas Propag., vol. AP-34, no. 3, pp. 276-280, 1986.
13. R. Roy and T. Kailath, "Esprit-estimation of signal parameters via rotational invariance techniques," IEEE Trans. Acoust., Speech, Signal Process., vol. 37, no. 7, pp. 984-995, 1989.
14. A. L. Chistov and Y. Grigoriev, "Complexity of quantifier elimination in the theory of algebraically closed fields," in Proc. 11th Symp. Math. Found. Comput. Sci., 1984, vol. 176, pp. 17-31.
15. M. Fazel, "Matrix Rank Minimization With Applications," Ph.D. dissertation, Electr. Eng. Dept., Stanford Univ., Stanford, CA, USA, 2002.
16. K. Mohan, M. Fazel, and B. Hassibi, "A simplified approach to recovery conditions for low rank matrices," in Proc. IEEE Int. Symp. Inform. Theory (ISIT), Jul./Aug. 2011, pp. 2318-2322.
17. S. Oymak and B. Hassibi, "New null space results and recovery thresholds for matrix rank minimization," 2010, arXiv preprint arXiv:1011. 6326.
18. L. Kong, L. Tuncel, and N. Xiu, "Sufficient conditions for low-rank matrix recovery, translated from sparse signal recovery," 2011, arXiv preprint arXiv:1106.3276.
19. S. Ma, D. Goldfarb, and L. Chen, "Fixed point and bregman iterative methods for matrix rank minimization," Math. Program., vol. 128, no. 1, pp. 321-353, 2011.
20. Z. Wen, W. Yin, and Y. Zhang, "Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm," Math. Program. Comput., vol. 4, no. 4, pp. 333-361, 2012.
21. J. T. Parker, P. Schniter, and V. Cevher, "Bilinear generalized approximate message passing," 2013, arXiv preprint arXiv:1310.2632.
22. R. H. Keshavan, A. Montanari, and S. Oh, "Matrix completion from a few entries," IEEE Trans. Inf. Theory, vol. 56, no. 6, pp. 2980-2998, 2010.
23. K. Lee and Y. Bresler, "Admira: Atomic decomposition for minimum rank approximation," IEEE Trans. Inf. Theory, vol. 56, no. 9, pp. 4402-4416, 2010.
24. D. Needell and J. A. Tropp, "Cosamp: Iterative signal recovery from incomplete and inaccurate samples," Appl. Comput. Harmonic Anal., vol. 26, no. 3, pp. 301-321, 2009.
25. H. Mohimani, M. Babaie-Zadeh, and C. Jutten, "A fast approach for overcomplete sparse decomposition based on smoothed norm," IEEE Trans. Signal Process., vol. 57, no. 1, pp. 289-301, Jan. 2009.
26. H. Ghasemi, M. Malek-Mohammadi, M. Babaie-Zadeh, and C. Jutten, "SRF: Matrix completion based on smoothed rank function," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), 2011, pp. 3672-3675.
27. E. J. Candés and T. Tao, "Decoding by linear programming," IEEE Trans. Inf. Theory, vol. 51, no. 12, pp. 4203-4215, 2005. (Pubitemid 41800353)
28. E. J. Candés, J. Romberg, and T. Tao, "Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information," IEEE Trans. Inf. Theory, vol. 52, no. 2, pp. 489-509, Feb. 2006. (Pubitemid 43174093)
29. D. L. Donoho, "Compressed sensing," IEEE Trans. Inf. Theory, vol. 52, no. 4, pp. 1289-1306, Apr. 2006.
30. Y. Zhang, "Theory of Compressive Sensing via Minimization: A Non-Rip Analysis and Extensions," Dept. Comput. Appl. Math., Rice Univ., Houston, TX, USA, Tech. Rep. tr08-11, 2008
31. [Online]. Available: http://www.caam.rice.edu/~zhang/reports/tr0811- revised.pdf
32. S. Oymak, M. A. Khajehnejad, and B. Hassibi, "Improved thresholds for rank minimizations," in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), May 2011, pp. 5988-5991.
33. A. S. Lewis and H. S. Sendov, "Nonsmooth analysis of singular values. Part I: Theory," Set-Valued Anal., vol. 13, no. 3, pp. 213-241, 2005. (Pubitemid 40965854)
34. A. Blake and A. Zisserman, Visual Reconstruction. Cambridge,MA, USA: MIT Press, 1987.
35. D. P. Bertsekas, Nonlinear Programming. Belmont, MA, USA: Athena Scientific, 1999.
36. A. S. Lewis, "The convex analysis of unitarily invariantmatrix norms," J. Convex Anal., vol. 2, pp. 173-183, 1995.
37. A. S. Lewis, "Convex analysis on the hermitian matrices," SIAM J. Optimization, vol. 6, pp. 164-177, 1996.
38. R. T. Rockafellar, Convex Analysis. Princeton, NJ, USA: Princeton Univ. Press, 1970.
39. H. Mohimani, M. Babaie-Zadeh, I. Gorodnitsky, and C. Jutten, Sparse Recovery Using Smoothed (SL0): Convergence Analysis [Online]. Available: arXiv:1001.5073
40. K. Dvijotham and M. Fazel, "A nullspace analysis of the nuclear norm heuristic for rank minimization," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Mar. 2010, pp. 3586-3589.
41. R. A. Horn and C. R. Johnson, Matrix Analysis. Cambridge,MA, USA: Cambridge Univ. Press, 1985.
42. Z. Lin, M. Chen, and Y. Ma, "The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices," Dept. Elect. Comput. Eng., Univ. Illinois, Urbana, IL, USA, Tech. Rep. uilueng- 09-2215, 2009.
43. K. C. Toh and S. Yun, "An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems," Pacific J. Optimization, vol. 6, pp. 615-640, 2010.