Eigenvectors of some large sample covariance matrix ensembles

DOI10.1007/S00440-010-0298-3zbMATH Open1229.60009arXiv0911.3010OpenAlexW3121682558MaRDI QIDQ644783FDOQ644783

Authors: Olivier Ledoit, S. Péché 

Publication date: 7 November 2011

Published in: Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)

Abstract: We consider sample covariance matrices $S_N=frac1pSigm{a}_N^{1/2}{X}_N{X}_N^{*}Sigm{a}_N^{1/2}$ where $X_N$ is a $Nimesp$ real or complex matrix with i.i.d. entries with finite $12^{mth}$ moment and $Sigm{a}_N$ is a $NimesN$ positive definite matrix. In addition we assume that the spectral measure of $Sigm{a}_N$ almost surely converges to some limiting probability distribution as $Noinfty$ and $p/Nogamma>0.$ We quantify the relationship between sample and population eigenvectors by studying the asymptotics of functionals of the type $frac1NextTr(g(Sigm{a}_N)(S_N-zI{)}^{-1})),$ where $I$ is the identity matrix, $g$ is a bounded function and $z$ is a complex number. This is then used to compute the asymptotically optimal bias correction for sample eigenvalues, paving the way for a new generation of improved estimators of the covariance matrix and its inverse.

Full work available at URL: https://arxiv.org/abs/0911.3010

Recommendations

• On asymptotics of eigenvectors of large sample covariance matrix
• scientific article; zbMATH DE number 3940318
• On the eigenvectors of large dimensional sample covariance matrices
• Functional CLT of eigenvectors for large sample covariance matrices
• Spectrum estimation for large dimensional covariance matrices using random matrix theory

zbMATH Keywords

Stieltjes transformprincipal component analysisasymptotic distributionrandom matrix theorybias correctionshrinkage estimatorsample covariance matrixeigenvectors and eigenvalues

Mathematics Subject Classification ID

Analysis of variance and covariance (ANOVA) (62J10) Random matrices (algebraic aspects) (15B52) Random matrices (probabilistic aspects) (60B20)

Cites Work

• A well-conditioned estimator for large-dimensional covariance matrices
• On the distribution of the largest eigenvalue in principal components analysis
• Strong convergence of the empirical distribution of eigenvalues of large dimensional random matrices
• Regularized estimation of large covariance matrices
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Title not available (Why is that?)
• Spectrum estimation for large dimensional covariance matrices using random matrix theory
• No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices
• Some hypothesis tests for the covariance matrix when the dimension is large compared to the sample size
• Analysis of the limiting spectral distribution of large dimensional random matrices
• Convergence rate of expected spectral distributions of large random matrices. II: Sample covariance matrices
• A limit theorem for the eigenvalues of product of two random matrices
• Limiting spectral distribution for a class of random matrices
• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• CLT for linear spectral statistics of large-dimensional sample covariance matrices.
• On asymptotics of eigenvectors of large sample covariance matrix
• Central limit theorem for signal-to-interference ratio of reduced rank linear receiver
• On the empirical distribution of eigenvalues of a class of large dimensional random matrices
• Title not available (Why is that?)
• Universality results for the largest eigenvalues of some sample covariance matrix ensembles
• Exact separation of eigenvalues of large dimensional sample covariance matrices
• The strong limits of random matrix spectra for sample matrices of independent elements
• Spectral Analysis of Networks with Random Topologies
• On the eigenvectors of large dimensional sample covariance matrices
• Some limit theorems on the eigenvectors of large dimensional sample covariance matrices
• Weak convergence of random functions defined by the eigenvectors of sample covariance matrices

Cited In (67)

• Principal Eigenportfolios for U.S. Equities
• High-Dimensional Analysis of Double Descent for Linear Regression with Random Projections
• Statistical diagonalization of a random biased Hamiltonian: the case of the eigenvectors
• High-dimensional covariance matrix estimation
• High-dimensional covariance matrices under dynamic volatility models: asymptotics and shrinkage estimation
• Matrix denoising: Bayes-optimal estimators via low-degree polynomials
• CORRELATION MATRIX OF EQUI-CORRELATED NORMAL POPULATION: FLUCTUATION OF THE LARGEST EIGENVALUE, SCALING OF THE BULK EIGENVALUES, AND STOCK MARKET
• A consistent estimator for confounding strength
• A family of flexible shrinkage estimators for the variances of high-dimensional gene expressions
• Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
• Large Dynamic Covariance Matrices
• Optimal cleaning for singular values of cross-covariance matrices
• Copula shrinkage and portfolio allocation in ultra-high dimensions
• CLT for spiked eigenvalues of a sample covariance matrix from high-dimensional Gaussian mean mixtures
• Properties of eigenvalues and eigenvectors of large-dimensional sample correlation matrices
• Ridge-type linear shrinkage estimation of the mean matrix of a high-dimensional normal distribution
• Eigenvalue distribution of large sample covariance matrices of linear processes
• Learning curves of generic features maps for realistic datasets with a teacher-student model*
• Fusing data depth with complex networks: community detection with prior information
• Spectral measures of spiked random matrices
• High-dimensional asymptotics of prediction: ridge regression and classification
• Spiked sample covariance matrices with possibly multiple bulk components
• Nonparametric eigenvalue-regularized precision or covariance matrix estimator
• Additive/multiplicative free subordination property and limiting eigenvectors of spiked additive deformations of Wigner matrices and spiked sample covariance matrices
• Eigenvalue distributions of variance components estimators in high-dimensional random effects models
• Limiting Eigenvectors of Outliers for Spiked Information-Plus-Noise Type Matrices
• Analytical nonlinear shrinkage of large-dimensional covariance matrices
• Subordination methods for free deconvolution
• Random matrix theory in statistics: a review
• Eigenvector dynamics under free addition
• Spiked separable covariance matrices and principal components
• The Dispersion Bias
• NOVELIST estimator of large correlation and covariance matrices and their inverses
• Convergence of eigenvector empirical spectral distribution of sample covariance matrices
• Asymptotic properties of principal component analysis and shrinkage-bias adjustment under the generalized spiked population model
• Improved Estimation of Eigenvalues and Eigenvectors of Covariance Matrices Using Their Sample Estimates
• On the dimension effect of regularized linear discriminant analysis
• High dimensional deformed rectangular matrices with applications in matrix denoising
• Spectrum estimation: a unified framework for covariance matrix estimation and PCA in large dimensions
• Projection-based high-dimensional sign test
• Comparison between two types of large sample covariance matrices
• Estimation of two high-dimensional covariance matrices and the spectrum of their ratio
• Analytic solution to variance optimization with no short positions
• High-dimensional general linear hypothesis tests via non-linear spectral shrinkage
• Recent advances in shrinkage-based high-dimensional inference
• Optimal estimation of a large-dimensional covariance matrix under Stein's loss
• On the eigenstructure of covariance matrices with divergent spikes
• Nonlinear shrinkage estimation of large-dimensional covariance matrices
• Free dynamics of feature learning processes
• Singular vector distribution of sample covariance matrices
• Two sample test for high-dimensional partially paired data
• Empirical spectral distribution of a matrix under perturbation
• Optimal shrinkage of eigenvalues in the spiked covariance model
• Estimating high dimensional covariance matrices: a new look at the Gaussian conjugate framework
• Two short pieces around the Wigner problem
• Title not available (Why is that?)
• Design-free estimation of integrated covariance matrices for high-frequency data
• Quadratic shrinkage for large covariance matrices
• Most powerful test against a sequence of high dimensional local alternatives
• Shrinkage estimation of large covariance matrices: keep it simple, statistician?
• An adaptable generalization of Hotelling's $T^2$ test in high dimension
• Surprises in high-dimensional ridgeless least squares interpolation
• Cleaning large correlation matrices: tools from random matrix theory
• Improving portfolios global performance using a cleaned and robust covariance matrix estimate
• Numerical implementation of the QuEST function
• Ensemble average of an arbitrary number of pairs of different eigenvalues using Grassmann integration
• Estimation of high-dimensional integrated covariance matrix based on noisy high-frequency data with multiple observations

This page was built for publication: Eigenvectors of some large sample covariance matrix ensembles

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q644783)