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

2023/08/28 by Nikita Puchkin, Puchkin, Nikita, Fedor Noskov +3 · 1 citation
Engineering · Mathematics · #FOS: Mathematics #Mathematical Approximation and Integration #Probability (math.PR) #Sparse and Compressive Sensing Techniques #Statistical Methods and Inference #Statistics Theory (math.ST)

paper · pdf · doi:10.48550/arxiv.2308.14739

openalex publication_date 2023/08/28 · openalex created_date 2023/08/31 · openalex updated_date 2026/07/28

Abstract

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(\rmTr(Σ²) / 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.

Cited by

• Riemannian Inexact Gradient Descent for Quadratic Discrimination

Related

• Dimension-free Structured Covariance Estimation
• Robust covariance estimation under L₄-L₂ norm equivalence
• Bootstrap confidence sets for spectral projectors of sample covariance
• Upper bounding the distance covariance of bounded random vectors
• How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?