## The Annals of Applied Probability

### Universality of covariance matrices

#### Abstract

In this paper we prove the universality of covariance matrices of the form $H_{N\times N}={X}^{\dagger}X$ where $X$ is an ${M\times N}$ rectangular matrix with independent real valued entries $x_{ij}$ satisfying $\mathbb{E}x_{ij}=0$ and $\mathbb{E}x^{2}_{ij}={\frac{1}{M}}$, $N,M\to \infty$. Furthermore it is assumed that these entries have sub-exponential tails or sufficiently high number of moments. We will study the asymptotics in the regime $N/M=d_{N}\in(0,\infty),\lim_{N\to\infty}d_{N}\neq0,\infty$. Our main result is the edge universality of the sample covariance matrix at both edges of the spectrum. In the case $\lim_{N\to\infty}d_{N}=1$, we only focus on the largest eigenvalue. Our proof is based on a novel version of the Green function comparison theorem for data matrices with dependent entries. En route to proving edge universality, we establish that the Stieltjes transform of the empirical eigenvalue distribution of $H$ is given by the Marcenko–Pastur law uniformly up to the edges of the spectrum with an error of order $(N\eta)^{-1}$ where $\eta$ is the imaginary part of the spectral parameter in the Stieltjes transform. Combining these results with existing techniques we also show bulk universality of covariance matrices. All our results hold for both real and complex valued entries.

#### Article information

Source
Ann. Appl. Probab., Volume 24, Number 3 (2014), 935-1001.

Dates
First available in Project Euclid: 23 April 2014

https://projecteuclid.org/euclid.aoap/1398258093

Digital Object Identifier
doi:10.1214/13-AAP939

Mathematical Reviews number (MathSciNet)
MR3199978

Zentralblatt MATH identifier
1296.15021

#### Citation

Pillai, Natesh S.; Yin, Jun. Universality of covariance matrices. Ann. Appl. Probab. 24 (2014), no. 3, 935--1001. doi:10.1214/13-AAP939. https://projecteuclid.org/euclid.aoap/1398258093

#### References

• [1] Bai, Z. D., Silverstein, J. W. and Yin, Y. Q. (1988). A note on the largest eigenvalue of a large-dimensional sample covariance matrix. J. Multivariate Anal. 26 166–168.
• [2] Bai, Z. D. and Yin, Y. Q. (1993). Limit of the smallest eigenvalue of a large-dimensional sample covariance matrix. Ann. Probab. 21 1275–1294.
• [3] Bao, Z., Pan, G. and Zhou, W. (2012). Tracy–Widom law for the extreme eigenvalues of sample correlation matrices. Electron. J. Probab. 17 1–32.
• [4] Ben Arous, G. and Péché, S. (2005). Universality of local eigenvalue statistics for some sample covariance matrices. Comm. Pure Appl. Math. 58 1316–1357.
• [5] Bourgade, P., Yau, H.-T. and Yin, J. (2013). Local circular law for random matrices. Probab. Theory Related Fields. To appear. DOI:10.1007/s00440-013-0514-z.
• [6] Cacciapuoti, C., Maltsev, A. and Schlein, B. (2013). Local Marchenko–Pastur law at the hard edge of sample covariance matrices. J. Math. Phys. 54 043302, 13.
• [7] Dieng, M. and Tracy, C. A. (2011). Application of random matrix theory to multivariate statistics. In Random Matrices, Random Processes and Integrable Systems 443–507. Springer, New York.
• [8] Dyson, F. J. (1962). A Brownian-motion model for the eigenvalues of a random matrix. J. Math. Phys. 3 1191–1198.
• [9] Edelman, A. (1991). The distribution and moments of the smallest eigenvalue of a random matrix of Wishart type. Linear Algebra Appl. 159 55–80.
• [10] Erdős, L., Knowles, A., Yau, H.-T. and Yin, J. (2012). Spectral statistics of Erdős–Rényi graphs II: Eigenvalue spacing and the extreme eigenvalues. Comm. Math. Phys. 314 587–640.
• [11] Erdős, L., Knowles, A., Yau, H.-T. and Yin, J. (2013). Spectral statistics of Erdős–Rényi graphs I: Local semicircle law. Ann. Probab. 41 2279–2375.
• [12] Erdős, L., Péché, S., Ramírez, J. A., Schlein, B. and Yau, H.-T. (2010). Bulk universality for Wigner matrices. Comm. Pure Appl. Math. 63 895–925.
• [13] Erdős, L., Schlein, B. and Yau, H.-T. (2011). Universality of random matrices and local relaxation flow. Invent. Math. 185 75–119.
• [14] Erdős, L., Schlein, B., Yau, H.-T. and Yin, J. (2012). The local relaxation flow approach to universality of the local statistics for random matrices. Ann. Inst. Henri Poincaré Probab. Statist. 48 1–46.
• [15] Erdős, L. and Yau, H.-T. (2012). A comment on the Wigner–Dyson–Mehta bulk universality conjecture for Wigner matrices. Electron. J. Probab. 17 1–5.
• [16] Erdős, L., Yau, H.-T. and Yin, J. (2011). Universality for generalized Wigner matrices with Bernoulli distribution. J. Comb. 2 15–81.
• [17] Erdős, L., Yau, H.-T. and Yin, J. (2012). Bulk universality for generalized Wigner matrices. Probab. Theory Related Fields 154 341–407.
• [18] Erdős, L., Yau, H.-T. and Yin, J. (2012). Rigidity of eigenvalues of generalized Wigner matrices. Adv. Math. 229 1435–1515.
• [19] Feldheim, O. N. and Sodin, S. (2010). A universality result for the smallest eigenvalues of certain sample covariance matrices. Geom. Funct. Anal. 20 88–123.
• [20] Götze, F. and Tikhomirov, A. (2004). Rate of convergence in probability to the Marchenko–Pastur law. Bernoulli 10 503–548.
• [21] Harding, M. C. (2008). Explaining the single factor bias of arbitrage pricing models in finite samples. Econom. Lett. 99 85–88.
• [22] Johnstone, I. M. (2001). On the distribution of the largest eigenvalue in principal components analysis. Ann. Statist. 29 295–327.
• [23] Johnstone, I. M. (2007). High dimensional statistical inference and random matrices. In International Congress of Mathematicians 307–333. Eur. Math. Soc., Zürich.
• [24] Johnstone, I. M. (2008). Multivariate analysis and Jacobi ensembles: Largest eigenvalue, Tracy–Widom limits and rates of convergence. Ann. Statist. 36 2638–2716.
• [25] Knowles, A. and Yin, J. (2013). The isotropic semicircle law and deformation of Wigner matrices. Comm. Pure Appl. Math. 66 1663–1749.
• [26] Knowles, A. and Yin, J. (2013). Eigenvector distribution of Wigner matrices. Probab. Theory Related Fields 155 543–582.
• [27] Marčenko, V. A. and Pastur, L. A. (1967). Distribution of eigenvalues for some sets of random matrices. Sb. Math. 4 457–483.
• [28] Onatski, A. (2009). Testing hypotheses about the numbers of factors in large factor models. Econometrica 77 1447–1479.
• [29] Oon Lee, J. and Yin, J. (2012). A necessary and sufficient condition for edge universality of Wigner matrices. Preprint. Available at arXiv:1206.2251.
• [30] Patterson, N., Price, A. L. and Reich, D. (2006). Population structure and eigenanalysis. PLoS Genet. 2 e190.
• [31] Péché, S. (2009). Universality results for the largest eigenvalues of some sample covariance matrix ensembles. Probab. Theory Related Fields 143 481–516.
• [32] Péché, S. (2012). Universality in the bulk of the spectrum for complex sample covariance matrices. Ann. Inst. Henri Poincaré Probab. Statist. 48 80–106.
• [33] Pillai, N. S. and Yin, J. (2012). Edge universality of correlation matrices. Ann. Statist. 40 1737–1763.
• [34] Soshnikov, A. (2002). A note on universality of the distribution of the largest eigenvalues in certain sample covariance matrices. J. Stat. Phys. 108 1033–1056.
• [35] Tao, T. and Vu, V. (2010). Random matrices: The distribution of the smallest singular values. Geom. Funct. Anal. 20 260–297.
• [36] Tao, T. and Vu, V. (2010). Random matrices: Universality of local eigenvalue statistics up to the edge. Comm. Math. Phys. 298 549–572.
• [37] Tao, T. and Vu, V. (2011). Random matrices: Universality of local eigenvalue statistics. Acta Math. 206 127–204.
• [38] Tao, T. and Vu, V. (2012). Random covariance matrices: Universality of local statistics of eigenvalues. Ann. Probab. 40 1285–1315.
• [39] Wang, K. (2012). Random covariance matrices: Universality of local statistics of eigenvalues up to the edge. Random Matrices: Theory Appl. 1 1150005, 24.
• [40] Yin, Y. Q., Bai, Z. D. and Krishnaiah, P. R. (1988). On the limit of the largest eigenvalue of the large-dimensional sample covariance matrix. Probab. Theory Related Fields 78 509–521.