Optimal cleaning for singular values of cross-covariance matrices

DOI10.1214/22-AAP1842MaRDI QIDQ6103997zbMATH OpenOpenAlexFDO

Authors Florent Benaych-Georges, Jean-Philippe Bouchaud, Marc Potters

Publication date 5 June 2023

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1901.05543

zbMATH Keywords

random matricescross-covariance matricesrotationally invariant estimator

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Random matrices (algebraic aspects) (15B52) Random matrices (probabilistic aspects) (60B20)

Abstract: We give a new algorithm for the estimation of the cross-covariance matrix $mathbbEX{Y}^{\prime }$ of two large dimensional signals $Xinmathbb{R}^n$, $Yinmathbb{R}^p$ in the context where the number $T$ of observations of the pair $(X,Y)$ is large but $n/T$ and $p/T$ are not supposed to be small. In the asymptotic regime where $n,p,T$ are large, with high probability, this algorithm is optimal for the Frobenius norm among rotationally invariant estimators, i.e. estimators derived from the empirical estimator by cleaning the singular values, while letting singular vectors unchanged.

Recommendations

• Spectrum estimation for large dimensional covariance matrices using random matrix theory
• A well-conditioned estimator for large-dimensional covariance matrices
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Optimal rates of convergence for covariance matrix estimation
• On the strong convergence of the optimal linear shrinkage estimator for large dimensional covariance matrix

Cites work

• A Dynamical Approach to Random Matrix Theory
• A well-conditioned estimator for large-dimensional covariance matrices
• Additive/multiplicative free subordination property and limiting eigenvectors of spiked additive deformations of Wigner matrices and spiked sample covariance matrices
• Cleaning large correlation matrices: tools from random matrix theory
• Eigenvectors of some large sample covariance matrix ensembles
• Estimation of low-rank covariance function
• High-dimensional probability. An introduction with applications in data science
• Large dimension forecasting models and random singular value spectra
• Local semicircle law for Wigner matrices
• Nonlinear shrinkage estimation of large-dimensional covariance matrices
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Random matrices and high-dimensional statistics: beyond covariance matrices
• Robust Estimates of Covariance Matrices in the Large Dimensional Regime
• Robust matrix completion
• Semicircle law on short scales and delocalization of eigenvectors for Wigner random matrices
• Spectral analysis of the Gram matrix of mixture models
• Spectrum estimation for large dimensional covariance matrices using random matrix theory
• Structured matrix estimation and completion
• The random matrix regime of Maronna's M-estimator with elliptically distributed samples

Cited in

(1)

• Matrix denoising: Bayes-optimal estimators via low-degree polynomials

This page was built for publication: Optimal cleaning for singular values of cross-covariance matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103997)