Convergence of eigenvector empirical spectral distribution of sample covariance matrices

Abstract

The eigenvector empirical spectral distribution (VESD) is a useful tool in studying the limiting behavior of eigenvalues and eigenvectors of covariance matrices. In this paper, we study the convergence rate of the VESD of sample covariance matrices to the deformed Marčenko-Pastur (MP) distribution. Consider sample covariance matrices of the form ${\Sigma }^{1/2}X{X}^{\ast }{\Sigma }^{1/2}$, where $X=(x_{ij})$ is an $M\times N$ random matrix whose entries are independent random variables with mean zero and variance $N^{-1}$, and $\Sigma$ is a deterministic positive-definite matrix. We prove that the Kolmogorov distance between the expected VESD and the deformed MP distribution is bounded by $N^{-1+\epsilon }$ for any fixed $\epsilon >0$, provided that the entries $\sqrt{N}{x}_{ij}$ have uniformly bounded 6th moments and $|N/M-1|\ge \tau$ for some constant $\tau >0$. This result improves the previous one obtained in \cite{XYZ2013}, which gave the convergence rate $O(N^{-1/2})$ assuming $i.i.d.$ $X$ entries, bounded 10th moment, $\Sigma =I$ and $M<N$. Moreover, we also prove that under the finite $8$th moment assumption, the convergence rate of the VESD is $O(N^{-1/2+\epsilon })$ almost surely for any fixed $\epsilon >0$, which improves the previous bound $N^{-1/4+\epsilon }$ in \cite{XYZ2013}.

To appear Annals of Statistics

References in corpus (8)

• High Dimensional Statistical Inference and Random Matrices
• Multivariate analysis and Jacobi ensembles: largest eigenvalue, Tracy--Widom limits and rates of convergence
• On asymptotics of eigenvectors of large sample covariance matrix
• Rotational invariant estimator for general noisy matrices
• The Tracy--Widom limit for the largest eigenvalues of singular complex Wishart matrices
• A necessary and sufficient condition for edge universality at the largest singular values of covariance matrices
• Edge universality of separable covariance matrices
• Local circular law for the product of a deterministic matrix with a random matrix

Cited by in corpus (5)

• Edge universality of separable covariance matrices
• Spiked separable covariance matrices and principal components
• Sample canonical correlation coefficients of high-dimensional random vectors: local law and Tracy-Widom limit
• Linear spectral statistics of eigenvectors of anisotropic sample covariance matrices
• Eigenvector overlaps in large sample covariance matrices and nonlinear shrinkage estimators