Minimax risk of matrix denoising by singular value thresholding

Annals of Statistics

Volumn 42, Issue 6, 2014, Pages 2413-2440

  Donoho, David ^a   Gavish, Matan ^a  

^a STANFORD UNIVERSITY   (United States)

Author keywords

Matrix completion from Gaussian measurements; Matrix denoising; Monotonicity of power functions of multivariate tests; Nuclear norm minimization; Optimal threshold; Phase transition; Singular value thresholding; Stein unbiased risk estimate

Indexed keywords

EID: 84908192014     PISSN: 00905364     EISSN: 21688966     Source Type: Journal    
DOI: 10.1214/14-AOS1257     Document Type: Article

References (25)

1. ANDERSON, T. W. (1955). The integral of a symmetric unimodal function over a symmetric convex set and some probability inequalities. Proc. Amer. Math. Soc. 6 170-176. MR0069229
2. CANDÈS, E. J., SING-LONG, C. A. and TRZASKO, J. D. (2013). Unbiased risk estimates for singular value thresholding and spectral estimators. IEEE Trans. Signal Process. 61 4643-4657. MR3105401
3. DAS GUPTA, S., ANDERSON, T. W. and MUDHOLKAR, G. S. (1964). Monotonicity of the power functions of some tests of the multivariate linear hypothesis. Ann. Math. Statist. 35 200-205. MR0158474
4. DONOHO, D. L. and GAVISH, M. (2013). Companion website for the article the phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising. Available at http://www.runmycode.org/CompanionSite/Site265.
5. DONOHO, D. and GAVISH, M. (2014). Supplement to "Minimax risk of matrix denoising by singular value thresholding." DOI:10.1214/14-AOS1257SUPP.
6. DONOHO, D. L., GAVISH, M. and MONTANARI, A. (2013). The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising. Proc. Natl. Acad. Sci. USA 110 8405-8410. MR3082268
7. DONOHO, D. L., JOHNSTONE, I. and MONTANARI, A. (2013). Accurate prediction of phase transitions in compressed sensing via a connection to minimax denoising. IEEE Trans. Inform. Theory 59 3396-3433. MR3061255
8. DONOHO, D. L. and JOHNSTONE, I. M. (1994). Minimax risk overl £-balls forl £-error. Probab. Theory Related Fields 303 277-303.
9. DONOHO, D. L., JOHNSTONE, I. M., HOCH, J. C. and STERN, A. S. (1992). Maximum entropy and the nearly black object. J. R. Stat. Soc. Ser. B Stat. Methodol. 54 41-81. MR1157714
10. GAVISH, M. and DONOHO, D. L. (2014). The optimal hard threshold for singular values is 4/V3. IEEE Trans. Inform. Theory 60 5040-5053.
11. GRANT, M. and BOYD, S. P. (2010). CVX: Matlab software for disciplined convex programming, version 2.0 beta. Available at http://cvxr.com/cvx, September 2013.
12. KOLTCHINSKII, V., LOUNICI, K. and TSYBAKOV, A. B. (2011). Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion. Ann. Statist. 39 2302-2329. MR2906869
13. LEWIS, A. S. (1995). The convex analysis of unitarily invariant matrix functions. J. Convex Anal. 2 173-183. MR1363368
14. LEWIS, A. S. and SENDOV, H. S. (2005). Nonsmooth analysis of singular values. I. Theory. Set-Valued Var. Anal. 13 213-241. MR2162512
15. MARCENKO, V. and PASTUR, L. (1967). Distribution of eigenvalues for some sets of random matrices. Mathematics USSR Sbornik 1 457-483.
16. OYMAK, S. and HASSIBI, B. (2010). New null space results and recovery thresholds for matrix rank minimization. Preprint. Available at http://arxiv.org/pdf/1011.6326v1.pdf.
17. OYMAK, S. and HASSIBI, B. (2012). On a relation between the minimax risk and the phase transitions of compressed recovery. In 2012 50th Annual Allerton Conference on Communication, Control, and Computing 1018-1025. IEEE, Piscataway, NJ. Available at http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6483330.
18. RECHT, B., FAZEL, M. and PARRILO, P. A. (2010). Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev. 52 471-501. MR2680543
19. RECHT, B., XU, W. and HASSIBI, B. (2008). Necessary and sufficient conditions for success of the nuclear norm heuristic for rank minimization. In Proceedings of the 47th IEEE Conference on Decision and Control Cancun, Mexico.
20. RECHT, B., XU, W. and HASSIBI, B. (2011). Null space conditions and thresholds for rank minimization. Math. Program. 127 175-202. MR2776714
21. ROHDE, A. and TSYBAKOV, A. B. (2011). Estimation of high-dimensional low-rank matrices. Ann. Statist. 39 887-930. MR2816342
22. SHABALIN, A. and NOBEL, A. (2010). Reconstruction of a low-rank matrix in the presence of Gaussian noise. Preprint. Available at arXiv:1007.4148.
23. STEIN, C. M. (1981). Estimation of the mean of a multivariate normal distribution. Ann. Statist. 9 1135-1151. MR0630098
24. TANNER, J. and WEI, K. (2013). Normalized iterative hard thresholding for matrix completion. SIAM J. Sci. Comput. 35 S104-S125. MR3120763
25. ZANELLA, A., CHIANI, M. and WIN, M. Z. (2009). On the marginal distribution of the eigenvalues of Wishart matrices. IEEE Transactions on Communications 57 1050-1060.