Convergence of eigenvector empirical spectral distribution of sample covariance matrices
arXiv:1705.03954 · doi:10.1214/19-AOS1832
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 , where is an random matrix whose entries are independent random variables with mean zero and variance , and is a deterministic positive-definite matrix. We prove that the Kolmogorov distance between the expected VESD and the deformed MP distribution is bounded by for any fixed , provided that the entries have uniformly bounded 6th moments and for some constant . This result improves the previous one obtained in \cite{XYZ2013}, which gave the convergence rate assuming entries, bounded 10th moment, and . Moreover, we also prove that under the finite th moment assumption, the convergence rate of the VESD is almost surely for any fixed , which improves the previous bound in \cite{XYZ2013}.
arXiv commentTo appear Annals of Statistics
References in corpus (19)
- Sparse principal component analysis and iterative thresholding
- Sparse PCA: Optimal rates and adaptive estimation
- Tracy--Widom limit for the largest eigenvalue of a large class of complex sample covariance matrices
- High Dimensional Statistical Inference and Random Matrices
- Universality of covariance matrices
- Multivariate analysis and Jacobi ensembles: largest eigenvalue, Tracy--Widom limits and rates of convergence
- Averaging Fluctuations in Resolvents of Random Band Matrices
- Universality for the largest eigenvalue of sample covariance matrices with general population
- Concentration of measure and spectra of random matrices: Applications to correlation matrices, elliptical distributions and beyond
- On asymptotics of eigenvectors of large sample covariance matrix
- A Necessary and Sufficient Condition for Edge Universality of Wigner matrices
- 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
- Large complex correlated Wishart matrices: Fluctuations and asymptotic independence at the edges
- Edge universality of separable covariance matrices
- Convergence rates of eigenvector empirical spectral distribution of large dimensional sample covariance matrix
- Local circular law for the product of a deterministic matrix with a random matrix
- Limiting spectral distribution of renormalized separable sample covariance matrices when
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