A useful variant of the Davis-Kahan theorem for statisticians

Biometrika

Volumn 102, Issue 2, 2015, Pages 315-323

  Yu, Y ^a   Wang, T ^a   Samworth, R J ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Davis Kahan theorem; Eigendecomposition; Matrix perturbation; Singular value decomposition

Indexed keywords

EID: 84941550517     PISSN: 00063444     EISSN: 14643510     Source Type: Journal    
DOI: 10.1093/biomet/asv008     Document Type: Article

References (22)

1. ANANDKUMAR, A., GE, R., HSU, D., KAKADE, S. M. & TELGARSKY, M. (2014). Tensor decompositions for learning latent variable models. J. Mach. Learn. Res. 15, 2773-832.
2. BAIK, J. & SILVERSTEIN, J. W. (2006). Eigenvalues of large sample covariance matrices of spiked population models. J. Mult. Anal. 97, 1382-408.
3. BAIK, J., BEN AROUS, G. & PÉCHÉ, S. (2005). Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices. Ann. Prob. 33, 1643-97.
4. CAI, T. T., ZHANG, C.-H. & ZHOU, H. H. (2010). Optimal rates of convergence for covariance matrix estimation. Ann. Statist. 38, 2118-44.
5. CAI, T. T., MA, Z. & WU, Y. (2013). Sparse PCA: Optimal rates and adaptive estimation. Ann. Statist. 41, 3074-110.
6. CANDÈS, E. J. & RECHT, B. (2009). Exact matrix completion via convex optimization. Foundat. Comp. Math. 9, 717-72.
7. CANDÈS, E. J., LI, X., MA, Y. & WRIGHT, J. (2009). Robust principal component analysis? J. ACM 58, 1-37.
8. DAVIS, C. & KAHAN, W. M. (1970). The rotation of eigenvectors by a pertubation. III. SIAM J. Numer. Anal. 7, 1-46.
9. DONATH, W. E. & HOFFMAN, A. J. (1973). Lower bounds for the partitioning of graphs. IBM J. Res. Dev. 17, 420-5.
10. FAN, J., LIAO, Y. & MINCHEVA, M. (2013). Large covariance estimation by thresholding principal orthogonal complements. J. R. Statist. Soc. B 75, 603-80.
11. KUKUSH, A., MARKOVSKY, I. & VAN HUFFEL, S. (2002). Consistent fundamental matrix estimation in a quadratic measurement error model arising in motion analysis. Comp. Statist. Data Anal. 41, 3-18.
12. ROHE, K., CHATTERJEE, S. & YU, B. (2011). Spectral clustering and the high-dimensional stochastic blockmodel. Ann. Statist. 39, 1878-915.
13. SHABALIN, A. A. & NOBEL, A. B. (2013). Reconstruction of a low-rank matrix in the presence of Gaussian noise. J. Mult. Anal. 118, 67-76.
14. STEWART, G. W. & SUN, J.-G. (1990). Matrix Perturbation Theory. San Diego: Academic Press.
15. SUN, T. & ZHANG, C.-H. (2012). Calibrated elastic regularization in matrix completion. Adv. Neural Info. Proces. Syst. 25, 863-71 F. Pereira, C. J. C. Burges, L. Bottou and K. Q. Weinberger, eds. New York: Curran Associates.
16. VAN HUFFEL, S. & VANDEWALLE, J. (1989). On the accuracy of total least squares and least squares techniques in the presence of errors on all data. Automatica 25, 765-9.
17. VON LUXBURG, U. (2007). A tutorial on spectral clustering. Statist. Comp. 17, 395-416.
18. VU, V. Q., CHO, J., LEI, J. & ROHE, K. (2013). Fantope projection and selection: A near-optimal convex relaxation of sparse PCA. Adv. Neural Info. Proces. Syst. 26, 2670-8, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani and K. Q. Weinberger, eds. New York: Curran Associates.
19. WEDIN, P.-Å. (1972). Perturbation bounds in connection with singular value decomposition. BIT Numer. Math. 12, 99-111.
20. WEYL, H. (1912). Das asymptotischeVerteilungsgesetz der Eigenwerte linearer partiellerDifferentialgleichungen (mit einer Anwendung auf der Theorie der Hohlraumstrahlung). Math. Ann. 71, 441-79.
21. WILKINSON, J. H. (1965). The Algebraic Eigenvalue Problem. Oxford: Clarendon Press.
22. ZOU, H., HASTIE, T. J. & TIBSHIRANI, R. J. (2006). Sparse principal components analysis. J. Comp. Graph. Statist. 15, 265-86.