Universality of Covariance Matrices

Natesh S. Pillai Harvard University Jun Yin University of Wisconsin

Probability mathscidoc:1608.28012

Annals of Applied Probability, 24, (3), 935-1001, 2011
In this paper we prove the universality of covariance matrices of the form $H_{Ntimes N}={X}^{dagger}X$ where $X$ is an ${Mtimes N}$ rectangular matrix with independent real valued entries $x_{ij}$ satisfying $mathbb{E}x_{ij}=0$ and $mathbb{E}x^2_{ij}={frac{1}{M}}$, $N$, $Mto infty$. 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 $N/M=d_Nin(0,infty),lim_{Ntoinfty}d_Nneq0,infty$. Our main result is the edge universality of the sample covariance matrix at both edges of the spectrum. In the case $lim_{Ntoinfty}d_N=1$, 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 $(Neta)^{-1}$ 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.
Covariance Matrice, edge universality, Marcenko-Pastur law, Stieltjes transform
[ Download ] [ 2016-08-23 14:42:27 uploaded by yinjun ] [ 1140 downloads ] [ 0 comments ] [ Cited by 34 ]
@inproceedings{natesh2011universality,
  title={Universality of Covariance Matrices},
  author={Natesh S. Pillai, and Jun Yin},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160823144227573143407},
  booktitle={Annals of Applied Probability},
  volume={24},
  number={3},
  pages={935-1001},
  year={2011},
}
Natesh S. Pillai, and Jun Yin. Universality of Covariance Matrices. 2011. Vol. 24. In Annals of Applied Probability. pp.935-1001. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160823144227573143407.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved