Hostname: page-component-586b7cd67f-dlnhk Total loading time: 0 Render date: 2024-11-23T22:43:25.150Z Has data issue: false hasContentIssue false
  • English
  • Français

Singular vector distribution of sample covariance matrices

Part of: Equilibrium statistical mechanics Special matrices

Published online by Cambridge University Press:  22 July 2019

Xiucai Ding
Xiucai Ding*
Affiliation:
University of Toronto
*
*Postal address: Department of Statistical Sciences, University of Toronto, Sidney Smith Hall, 100 St. George Street, Toronto, ON M5S 3G3, Canada.
Get access Rights & Permissions [Opens in a new window]

Abstract

We consider a class of sample covariance matrices of the form Q = TXX*T*, where X = (xij) is an M×N rectangular matrix consisting of independent and identically distributed entries, and T is a deterministic matrix such that T*T is diagonal. Assuming that M is comparable to N, we prove that the distribution of the components of the right singular vectors close to the edge singular values agrees with that of Gaussian ensembles provided the first two moments of xij coincide with the Gaussian random variables. For the right singular vectors associated with the bulk singular values, the same conclusion holds if the first four moments of xij match those of the Gaussian random variables. Similar results hold for the left singular vectors if we further assume that T is diagonal.

Keywords

Random matrix theorysingular vector distributiondeformed Marcenko–Pastur law

MSC classification

Primary: 15B52: Random matrices
Secondary: 82B44: Disordered systems (random Ising models, random Schrödinger operators, etc.)
Type
Original Article
Information
Advances in Applied Probability , Volume 51 , Issue 1 , March 2019 , pp. 236 - 267
Copyright
© Applied Probability Trust 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

The supplementary material for this article can be found at http://doi.org/10.1017/apr.2019.10.

References

Abbe, E., Fan, J., Wang, K. and Zhong, Y. (2017). Entrywise eigenvector analysis of random matrices with low expected rank. Preprint. Available at https://arxiv.org/abs/1709.09565.Google Scholar
Bai, Z. D. and Silverstein, J. W. (2010). Spectral Analysis of Large Dimensional Random Matrices, 2nd edn. Springer, New York.CrossRefGoogle Scholar
Bai, Z. D., Miao, B. Q. and Pan, G. M. (2007). On asymptotics of eigenvectors of large sample covariance matrix. Ann. Prob. 35, 1532–1572.CrossRefGoogle Scholar
Baik, J., Ben Arous, G. and Péché, S. (2005). Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices. Ann. Prob. 33, 1643–1697.CrossRefGoogle Scholar
Bao, Z., Pan, G. and Zhou, W. (2015). Universality for the largest eigenvalue of sample covariance matrices with general population. Ann. Statist. 43, 382–421.CrossRefGoogle Scholar
Benaych-Georges, F. and Nadakuditi, R. R. (2011). The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices. Adv. Math. 227, 494–521.CrossRefGoogle Scholar
Benaych-Georges, F., Guionnet, A. and Maida, M. (2011). Fluctuations of the extreme eigenvalues of finite rank deformations of random matrices. Electron. J. Prob. 16, 1621–1662.CrossRefGoogle Scholar
Bloemendal, A., Knowles, A., Yau, H.-T. and Yin, J. (2016). On the principal components of sample covariance matrices. Prob. Theory Relat. Fields 164, 459–552.CrossRefGoogle Scholar
Bloemendal, A. et al. (2014). Isotropic local laws for sample covariance and generalized Wigner matrices. Electron. J. Prob. 19, pp. 53.Google Scholar
Bourgade, P. and Yau, H.-T. (2017). The eigenvector moment flow and local quantum unique ergodicity. Commun. Math. Phys. 350, 231–278.CrossRefGoogle Scholar
Cai, T. T., Ren, Z. and Zhou, H. H. (2016). Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation. Electron. J. Statist. 10, 1–59.CrossRefGoogle Scholar
Capitaine, M., Donati-Martin, C. and Féral, D. (2009). The largest eigenvalues of finite rank deformation of large Wigner matrices: convergence and nonuniversality of the fluctuations. Ann. Prob. 37, 1–47.CrossRefGoogle Scholar
Ding, X. (2017). High dimensional deformed rectangular matrices with applications in matrix denoising. Preprint. Available at https://arxiv.org/abs/1702.06975.Google Scholar
Ding, X. (2019). Singular vector distribution of sample covariance matrices. Supplementary material. Available at http://doi.org/10.1017/apr.2019.10.CrossRefGoogle Scholar
Ding, X. and Sun, Q. (2018). Modified Multidimensional Scaling and High Dimensional Clustering. Available at https://arxiv.org/abs/1810.10172.Google Scholar
Ding, X. and Yang, F. (2018). A necessary and sufficient condition for edge universality at the largest singular values of covariance matrices. Ann. Appl. Prob. 28, 1679–1738.CrossRefGoogle Scholar
El Karoui, N. (2007). Tracy-Widom limit for the largest eigenvalue of a large class of complex sample covariance matrices. Ann. Prob. 35, 663–714.CrossRefGoogle Scholar
Erdös, L., Yau, H.-T. and Yin, J. (2012). Rigidity of eigenvalues of generalized Wigner matrices. Adv. Math. 229, 1435–1515.CrossRefGoogle Scholar
Erdös, L., Ramirez, J. A., Schlein, B. and Yau, H.-T. (2010). Universality of sine-kernel for Wigner matrices with a small Gaussian perbubation. Electron. J. Prob. 15, 526–603.CrossRefGoogle Scholar
Fan, J. and Zhong, Y. (2018). Optimal subspace estimation using overidentifying vectors via generalized method of moments Available at https://arxiv.org/abs/1805.02826.Google Scholar
Fan, J., Wang, W. and Zhong, Y. (2017). An ℓ ∞ eigenvector perturbation bound and its application to robust covariance estimation. J. Machine Learning Res. 18, pp. 42.Google Scholar
Golub, G. H. and Van Loan, C. F. (2013). Matrix Computations, 4th edn. John Hopkins University Press, Baltimore, MD.Google Scholar
Johnstone, I. M. (2001). On the distribution of the largest eigenvalue in principal components analysis. Ann. Statist. 29, 295–327.CrossRefGoogle Scholar
Knowles, A. and Yin, J. (2013). Eigenvector distribution of Wigner matrices. Prob. Theory Relat. Fields 155, 543–582.CrossRefGoogle Scholar
Knowles, A. and Yin, J. (2014). The outliers of a deformed Wigner matrix. Ann. Prob. 42, 1980–2031.CrossRefGoogle Scholar
Knowles, A. and Yin, J. (2017). Anisotropic local laws for random matrices. Prob. Theory Relat. Fields 169, 257–352.CrossRefGoogle Scholar
Ledoit, O. and Péché, S. (2011). Eigenvectors of some large sample covariance matrix ensembles. Prob. Theory Relat. Fields 151, 233–264.CrossRefGoogle Scholar
Lee, J. O. and Schnelli, K. (2016). Tracy-Widom distribution for the largest eigenvalue of real sample covariance matrices with general population. Ann. Appl. Prob. 26, 3786–3839.CrossRefGoogle Scholar
Li, G., Tang, M., Charon, N. and Priebe, C. E. (2018). A central limit theorem for classical multidimensional scaling. Available at https://arxiv.org/abs/1804.00631.Google Scholar
Marčenko, V. A. and Pastur, L. A. (1967). Distribution of eigenvalues for some sets of random matrices. Math. USSR-Sbornik 1, 457.CrossRefGoogle Scholar
O’Rourke, S., Vu, V. and Wang, K. (2016). Eigenvectors of random matrices: a survey. J. Combinatorial Theory Ser A 144, 361–442.CrossRefGoogle Scholar
Pillai, N. S. and Yin, J. (2012). Edge universality of correlation matrices. Ann. Statist. 40, 1737–1763.CrossRefGoogle Scholar
Pillai, N. S. and Yin, J. (2014). Universality of covariance matrices. Ann. Appl. Prob. 24, 935–1001.CrossRefGoogle Scholar
Silverstein, J. W. (1984). Some limit theorems on the eigenvectors of large-dimensional sample covariance matrices. J. Multivariate Anal. 15, 295–324.CrossRefGoogle Scholar
Silverstein, J. W. (2009). The Stieltjes transform and its role in eigenvalue behavior of large dimensional random matrices. in Random Matrix Theory and its Applications, World Scientific, Hackensack,CrossRefGoogle Scholar
Silverstein, J. W. and Choi, S.-I. (1995). Analysis of the limiting spectral distribution of large dimensional random matrices. J. Multivariate Anal. 54, 295–309.CrossRefGoogle Scholar
Tao, T. and Vu, V. (2012). Random matrices: universal properties of eigenvectors. Random Matrices Theory Appl. 1, pp. 27.CrossRefGoogle Scholar
Tracy, C. A. and Widom, H. (1996). On orthogonal and symplectic matrix ensembles. Commun. Math. Phys. 177, 727–754.CrossRefGoogle Scholar
Xi, H., Yang, F. and Yin, J. (2017). Local circular law for the product of a deterministic matrix with a random matrix. Electron. J. Prob. 22, pp. 77.CrossRefGoogle Scholar
Yao, J., Zheng, S. and Bai, Z. (2015). Large Sample Covariance Matrices and High-Dimensional Data Analysis. Cambridge University Press.CrossRefGoogle Scholar
Zhong, Y. and Boumal, N. (2018). Near-optimal Bounds For Phase Synchronization. SIAM J. Optimization 28, 989–1016.CrossRefGoogle Scholar
Supplementary material: PDF

Ding supplementary material

Supplementary material 1
Download Ding supplementary material(PDF)
PDF 256.5 KB