How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?

02/17/2017
by   Andreas Loukas, et al.
0

How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix? For a wide family of distributions, including distributions with finite second moment and distributions supported in a centered Euclidean ball, we prove that the inner product between eigenvectors of the sample and actual covariance matrices decreases proportionally to the respective eigenvalue distance. Our findings imply non-asymptotic concentration bounds for eigenvectors, eigenspaces, and eigenvalues. They also provide conditions for distinguishing principal components based on a constant number of samples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/16/2018

Generalized Four Moment Theorem and an Application to CLT for Spiked Eigenvalues of Large-dimensional Covariance Matrices

We consider a more generalized spiked covariance matrix Σ, which is a ge...
research
02/14/2012

New Probabilistic Bounds on Eigenvalues and Eigenvectors of Random Kernel Matrices

Kernel methods are successful approaches for different machine learning ...
research
01/30/2016

Spectrum Estimation from Samples

We consider the problem of approximating the set of eigenvalues of the c...
research
05/29/2019

Spiked separable covariance matrices and principal components

We introduce a class of separable sample covariance matrices of the form...
research
05/21/2018

Lassoing Eigenvalues

The properties of penalized sample covariance matrices depend on the cho...
research
03/08/2019

Random Matrix-Improved Estimation of the Wasserstein Distance between two Centered Gaussian Distributions

This article proposes a method to consistently estimate functionals 1/p∑...
research
07/10/2014

An eigenanalysis of data centering in machine learning

Many pattern recognition methods rely on statistical information from ce...

Please sign up or login with your details

Forgot password? Click here to reset