Robust sparse covariance estimation by thresholding Tyler's M-estimator

DOI10.1214/18-AOS1793MaRDI QIDQ2176609zbMATH OpenFDO

Authors John Goes, Gilad Lerman, Boaz Nadler

Publication date 5 May 2020

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

Full work available at URL https://arxiv.org/abs/1706.08020, https://projecteuclid.org/euclid.aos/1581930127

zbMATH Keywords

covariance matrix estimationelliptical distributionsparsityspectral normthresholdingTyler's M-estimator

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Nonparametric robustness (62G35) Estimation in multivariate analysis (62H12) Inference from stochastic processes and spectral analysis (62M15)

Abstract: Estimating a high-dimensional sparse covariance matrix from a limited number of samples is a fundamental problem in contemporary data analysis. Most proposals to date, however, are not robust to outliers or heavy tails. Towards bridging this gap, in this work we consider estimating a sparse shape matrix from $n$ samples following a possibly heavy tailed elliptical distribution. We propose estimators based on thresholding either Tyler's M-estimator or its regularized variant. We derive bounds on the difference in spectral norm between our estimators and the shape matrix in the joint limit as the dimension $p$ and sample size $n$ tend to infinity with $p/nogamma>0$. These bounds are minimax rate-optimal. Results on simulated data support our theoretical analysis.

Recommendations

• Structured robust covariance estimation
• Trimmed estimators for large dimensional sparse covariance matrices
• High-dimensional covariance estimation under the presence of outliers
• Minimax optimal estimation of high-dimensional sparse covariance matrices with missing data
• Robust covariance and scatter matrix estimation under Huber's contamination model

Cites work

• \(M\)-functionals of multivariate scatter
• A cautionary note on robust covariance plug-in methods
• A distribution-free M-estimator of multivariate scatter
• A generalization of Tyler's M-estimators to the case of incomplete data
• Adaptive thresholding for sparse covariance matrix estimation
• Concentration of the spectral measure for large matrices
• Covariance regularization by thresholding
• Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
• Generalized Robust Shrinkage Estimator and Its Application to STAP Detection Problem
• Generalized thresholding of large covariance matrices
• Hanson-Wright inequality and sub-Gaussian concentration
• scientific article; zbMATH DE number 3673370 (Why is no real title available?)
• scientific article; zbMATH DE number 45785 (Why is no real title available?)
• scientific article; zbMATH DE number 1964693 (Why is no real title available?)
• scientific article; zbMATH DE number 3354336 (Why is no real title available?)
• Large dimensional analysis and optimization of robust shrinkage covariance matrix estimators
• Large Dimensional Analysis of Robust M-Estimators of Covariance With Outliers
• Local operator theory, random matrices and Banach spaces.
• Marčenko-Pastur law for Tyler's M-estimator
• Minimax estimation of large covariance matrices under _1-norm
• New algorithms for M-estimation of multivariate scatter and location
• On the theory of elliptically contoured distributions
• On Tyler's M-functional of scatter in high dimension
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Optimal rates of convergence for sparse covariance matrix estimation
• Redescending M-estimates of multivariate location and scatter
• Regularized <formula formulatype="inline"><tex Notation="TeX">$M$</tex> </formula>-Estimators of Scatter Matrix
• Regularized Tyler's Scatter Estimator: Existence, Uniqueness, and Algorithms
• Robust and efficient estimation of multivariate scatter and location
• Robust covariance and scatter matrix estimation under Huber's contamination model
• Robust Estimates of Covariance Matrices in the Large Dimensional Regime
• Robust estimation of high-dimensional covariance and precision matrices
• Robust Estimation of Structured Covariance Matrix for Heavy-Tailed Elliptical Distributions
• Robust m-estimators of multivariate location and scatter
• Robust Shrinkage Estimation of High-Dimensional Covariance Matrices
• Robust sparse covariance estimation by thresholding Tyler's M-estimator
• Robust Statistics
• Second order statistics of robust estimators of scatter. Application to GLRT detection for elliptical signals
• Sparsistency and rates of convergence in large covariance matrix estimation
• Statistical analysis for the angular central Gaussian distribution on the sphere
• Structured robust covariance estimation
• Symmetrised M-estimators of multivariate scatter
• The random matrix regime of Maronna's M-estimator with elliptically distributed samples
• The sample covariance is not efficient for elliptical distributions
• Tyler's Covariance Matrix Estimator in Elliptical Models With Convex Structure
• Unified Framework to Regularized Covariance Estimation in Scaled Gaussian Models

Cited in

(24)

• High-dimensional covariance estimation under the presence of outliers
• Robust covariance and scatter matrix estimation under Huber's contamination model
• Robust sparse covariance estimation by thresholding Tyler's M-estimator
• User-friendly covariance estimation for heavy-tailed distributions
• Large dimensional analysis and optimization of robust shrinkage covariance matrix estimators
• An overview of heavy-tail extensions of multivariate Gaussian distribution and their relations
• Robust estimation of reduced rank models to large spatial datasets
• Rejoinder to “A Tuning-Free Robust and Efficient Approach to High-Dimensional Regression”
• Trimmed estimators for large dimensional sparse covariance matrices
• Structured robust covariance estimation
• Robust Shape Matrix Estimation for High-Dimensional Compositional Data with Application to Microbial Inter-Taxa Analysis
• Tyler's and Maronna's M-estimators: non-asymptotic concentration results
• Robust Covariance Matrix Estimation for High-Dimensional Compositional Data with Application to Sales Data Analysis
• Covariance Model with General Linear Structure and Divergent Parameters
• Robust semiparametric modeling of mean and covariance in longitudinal data
• A review of Tyler's shape matrix and its extensions
• Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction
• Covariance operator estimation: sparsity, lengthscale, and ensemble Kalman filters
• Tests for Large-Dimensional Shape Matrices via Tyler’s M Estimators
• The Dyson equalizer: adaptive noise stabilization for low-rank signal detection and recovery
• Robust estimation of matrix-valued time series autoregressive model
• High dimensional T-type estimator for robust covariance matrix estimation with applications to elliptical factor models
• Testing Elliptical Models in High Dimensions
• A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery

This page was built for publication: Robust sparse covariance estimation by thresholding Tyler's M-estimator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2176609)