Robust covariance estimation under L₄-L₂ norm equivalence

DOI10.1214/19-AOS1862MaRDI QIDQ2196239zbMATH OpenOpenAlexFDO

Authors Shahar Mendelson, Nikita Zhivotovskiy

Publication date 28 August 2020

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1809.10462, https://projecteuclid.org/euclid.aos/1594972833

zbMATH Keywords

covariance estimationrobust estimationmedian of means

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Nonparametric tolerance and confidence regions (62G15) Analysis of variance and covariance (ANOVA) (62J10)

Abstract: Let $X$ be a centered random vector taking values in $mathbb{R}^d$ and let $Sigma=mathbbE(XotimesX)$ be its covariance matrix. We show that if $X$ satisfies an $L_4-L_2$ norm equivalence, there is a covariance estimator $hatSigma$ that exhibits the optimal performance one would expect had $X$ been a gaussian vector. The procedure also improves the current state-of-the-art regarding high probability bounds in the subgaussian case (sharp results were only known in expectation or with constant probability). In both scenarios the new bound does not depend explicitly on the dimension $d$, but rather on the effective rank of the covariance matrix $Sigma$.

Recommendations

• Robust modifications of U-statistics and applications to covariance estimation problems
• Estimating covariance and precision matrices along subspaces
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Structured robust covariance estimation
• Robust covariance and scatter matrix estimation under Huber's contamination model

Cites work

• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• An introduction to matrix concentration inequalities
• Challenging the empirical mean and empirical variance: a deviation study
• Concentration inequalities and moment bounds for sample covariance operators
• Empirical processes with a bounded \(\psi_1\) diameter
• Facial structures of schattenp-Norms
• High-dimensional covariance matrix estimation with missing observations
• Multivariate T-Distributions and Their Applications
• Near-optimal mean estimators with respect to general norms
• On some extensions of Bernstein's inequality for self-adjoint operators
• On the infimum convolution inequality
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Robust modifications of U-statistics and applications to covariance estimation problems
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Upper and lower bounds for stochastic processes. Modern methods and classical problems
• Upper bounds on product and multiplier empirical processes

Cited in

(41)

• Robust modifications of U-statistics and applications to covariance estimation problems
• New challenges in covariance estimation: multiple structures and coarse quantization
• Covariance estimation under one-bit quantization
• Finite-sample analysis of \(M\)-estimators using self-concordance
• Sub-Gaussian estimators of the mean of a random vector
• Suboptimality of constrained least squares and improvements via non-linear predictors
• Robust Regression with Covariate Filtering: Heavy Tails and Adversarial Contamination
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Robust covariance estimation for approximate factor models
• Sharper dimension-free bounds on the Frobenius distance between sample covariance and its expectation
• Robustifying Markowitz
• Covariance estimation for distributions with \({2+\varepsilon}\) moments
• Structure preservation via the Wasserstein distance
• Estimating covariance and precision matrices along subspaces
• A new robust covariance matrix estimation for high-dimensional microbiome data
• The geometric median and applications to robust mean estimation
• scientific article; zbMATH DE number 7370530 (Why is no real title available?)
• Gaussian differentially private robust mean estimation and inference
• Robust subgaussian estimation with VC-dimension
• Distribution-free robust linear regression
• Robust estimation of covariance matrices: adversarial contamination and beyond
• Covariance estimation under missing observations and L₄ - L₂ moment equivalence
• Stable recovery and the coordinate small-ball behaviour of random vectors
• The projected covariance measure for assumption-lean variable significance testing
• Robust \(k\)-means clustering for distributions with two moments
• Quantitative limit theorems and bootstrap approximations for empirical spectral projectors
• Approximating \(L_p\) unit balls via random sampling
• Tyler's and Maronna's M-estimators: non-asymptotic concentration results
• Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle
• Robust covariance estimation for distributed principal component analysis
• Nearly optimal robust mean estimation via empirical characteristic function
• Trimmed sample means for robust uniform mean estimation and regression
• Covariance estimation: optimal dimension-free guarantees for adversarial corruption and heavy tails
• Mean estimation and regression under heavy-tailed distributions: A survey
• Rank-based correlation matrix estimation for high dimensional microbiome data
• Uniform bounds for robust mean estimators
• Sparse linear regression when noises and covariates are heavy-tailed and contaminated by outliers
• Sharp concentration of simple random tensors
• Improved covariance estimation: optimal robustness and sub-Gaussian guarantees under heavy tails
• Statistically optimal robust mean and covariance estimation for anisotropic gaussians
• User-friendly covariance estimation for heavy-tailed distributions

This page was built for publication: Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196239)