Dimension-free bounds for sums of dependent matrices and operators with heavy-tailed distributions

DOI10.1214/24-ejs2224arXiv2210.09756OpenAlexW4392522215MaRDI QIDQ6200904

Pierre Alquier, Masaaki Imaizumi, Shogo H. Nakakita

Publication date: 25 March 2024

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2210.09756

zbMATH Keywords

heavy-tailed distributionrandom matrixhigh-dimensiondependent process

Mathematics Subject Classification ID

Processes with independent increments; Lévy processes (60G51) Estimation in multivariate analysis (62H12) Matrix methods for summability (40C05)

Cites Work

• Unnamed Item
• Covariance estimation for distributions with \({2+\varepsilon}\) moments
• Model selection for weakly dependent time series forecasting
• Concentration inequalities and moment bounds for sample covariance operators
• Moment bounds for large autocovariance matrices under dependence
• \(L_{p}\)-moments of random vectors via majorizing measures
• Weakly dependent chains with infinite memory
• Optimal rates of convergence for covariance matrix estimation
• Random vectors in the isotropic position
• Robust dimension-free Gram operator estimates
• New dependence coefficients. Examples and applications to statistics
• Adaptive estimation of a quadratic functional by model selection.
• Challenging the empirical mean and empirical variance: a deviation study
• Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching
• On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
• Structured random matrices
• On the singular values of random matrices
• Weak dependence. With examples and applications.
• Non-strong mixing autoregressive processes
• Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles
• Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes
• High-Dimensional Probability
• <scp>Sub‐Gaussian</scp> Matrices on Sets: Optimal Tail Dependence and Applications
• Benign overfitting in linear regression
• A Simple Tool for Bounding the Deviation of Random Matrices on Geometric Sets
• Compressed sensing

This page was built for publication: Dimension-free bounds for sums of dependent matrices and operators with heavy-tailed distributions