Relative perturbation bounds with applications to empirical covariance operators
Probability
2022-03-03 v4
Abstract
The goal of this paper is to establish relative perturbation bounds, tailored for empirical covariance operators. Our main results are expansions for empirical eigenvalues and spectral projectors, leading to concentration inequalities and limit theorems. One of the key ingredients is a specific separation measure for population eigenvalues, which we call the relative rank, giving rise to a sharp invariance principle in terms of limit theorems, concentration inequalities and inconsistency results. Our framework is very general, requiring only moments and allows for a huge variety of dependence structures.
Keywords
Cite
@article{arxiv.1802.02869,
title = {Relative perturbation bounds with applications to empirical covariance operators},
author = {Moritz Jirak and Martin Wahl},
journal= {arXiv preprint arXiv:1802.02869},
year = {2022}
}
Comments
58 pages