Sharper dimension-free bounds on the Frobenius distance between sample covariance and its expectation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Puchkin, Nikita, Noskov, Fedor, Spokoiny, Vladimir
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916383992840192
author Puchkin, Nikita
Noskov, Fedor
Spokoiny, Vladimir
author_facet Puchkin, Nikita
Noskov, Fedor
Spokoiny, Vladimir
contents We study properties of a sample covariance estimate $\widehat Σ$ given a finite sample of $n$ i.i.d. centered random elements in $\R^d$ with the covariance matrix $Σ$. We derive dimension-free bounds on the squared Frobenius norm of $(\widehatΣ- Σ)$ under reasonable assumptions. For instance, we show that $\smash{\|\widehatΣ- Σ\|_{\rm F}^2}$ differs from its expectation by at most $\smash{\mathcal O({\rm{Tr}}(Σ^2) / n)}$ with overwhelming probability, which is a significant improvement over the existing results. This allows us to establish the concentration phenomenon for the squared Frobenius distance between the covariance and its empirical counterpart in the case of moderately large effective rank of $Σ$.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14739
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sharper dimension-free bounds on the Frobenius distance between sample covariance and its expectation
Puchkin, Nikita
Noskov, Fedor
Spokoiny, Vladimir
Probability
Statistics Theory
We study properties of a sample covariance estimate $\widehat Σ$ given a finite sample of $n$ i.i.d. centered random elements in $\R^d$ with the covariance matrix $Σ$. We derive dimension-free bounds on the squared Frobenius norm of $(\widehatΣ- Σ)$ under reasonable assumptions. For instance, we show that $\smash{\|\widehatΣ- Σ\|_{\rm F}^2}$ differs from its expectation by at most $\smash{\mathcal O({\rm{Tr}}(Σ^2) / n)}$ with overwhelming probability, which is a significant improvement over the existing results. This allows us to establish the concentration phenomenon for the squared Frobenius distance between the covariance and its empirical counterpart in the case of moderately large effective rank of $Σ$.
title Sharper dimension-free bounds on the Frobenius distance between sample covariance and its expectation
topic Probability
Statistics Theory
url https://arxiv.org/abs/2308.14739