Abstract: This paper studies the limiting behavior of Tyler's M-estimator for the scatter matrix, in the regime that the number of samples and their dimension both go to infinity, and converges to a constant with . We prove that when the data samples are identically and independently generated from the Gaussian distribution , the operator norm of the difference between a properly scaled Tyler's M-estimator and tends to zero. As a result, the spectral distribution of Tyler's M-estimator converges weakly to the Marv{c}enko-Pastur distribution.
Recommendations
- Tyler's and Maronna's M-estimators: non-asymptotic concentration results
- Marčenko-Pastur law for Kendall's tau
- Semicircle law of Tyler's \(M\)-estimator for scatter
- Law of the Iterated Logarithm and Invariance Principle for M-Estimators
- Marcinkiewicz-Zygmund and ordinary strong laws for empirical distribution functions and plug-in estimators
- Marcinkiewicz strong laws for linear statistics
- A constant regression characterization of a Marchenko-Pastur law
- Convergence and Fluctuations of Regularized Tyler Estimators
Cites work
- scientific article; zbMATH DE number 5204610 (Why is no real title available?)
- A distribution-free M-estimator of multivariate scatter
- Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond
- DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
- Geodesic Convexity and Covariance Estimation
- Large Dimensional Analysis of Robust M-Estimators of Covariance With Outliers
- Local operator theory, random matrices and Banach spaces.
- On Tyler's \(M\)-functional of scatter in high dimension
- Robust Estimates of Covariance Matrices in the Large Dimensional Regime
- Robust Shrinkage Estimation of High-Dimensional Covariance Matrices
- Robust spiked random matrices and a robust G-MUSIC estimator
- Robust subspace recovery by Tyler's M-estimator
- Second order statistics of robust estimators of scatter. Application to GLRT detection for elliptical signals
- Semicircle law of Tyler's \(M\)-estimator for scatter
- The random matrix regime of Maronna's M-estimator with elliptically distributed samples
Cited in
(12)- Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
- Consistency and asymptotic normality of M-estimates of scatter on Grassmann manifolds
- User-friendly covariance estimation for heavy-tailed distributions
- Robust sparse covariance estimation by thresholding Tyler's M-estimator
- A review of Tyler's shape matrix and its extensions
- An overview of heavy-tail extensions of multivariate Gaussian distribution and their relations
- Robust modifications of U-statistics and applications to covariance estimation problems
- A concentration of measure and random matrix approach to large-dimensional robust statistics
- Tyler's and Maronna's M-estimators: non-asymptotic concentration results
- The random matrix regime of Maronna's M-estimator with elliptically distributed samples
- scientific article; zbMATH DE number 7306864 (Why is no real title available?)
- Semicircle law of Tyler's \(M\)-estimator for scatter
This page was built for publication: Marčenko-Pastur law for Tyler's M-estimator
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q290712)