All-in-one robust estimator of the Gaussian mean
From MaRDI portal
Publication:2131271
Abstract: The goal of this paper is to show that a single robust estimator of the mean of a multivariate Gaussian distribution can enjoy five desirable properties. First, it is computationally tractable in the sense that it can be computed in a time which is at most polynomial in dimension, sample size and the logarithm of the inverse of the contamination rate. Second, it is equivariant by translations, uniform scaling and orthogonal transformations. Third, it has a high breakdown point equal to , and a nearly-minimax-rate-breakdown point approximately equal to . Fourth, it is minimax rate optimal, up to a logarithmic factor, when data consists of independent observations corrupted by adversarially chosen outliers. Fifth, it is asymptotically efficient when the rate of contamination tends to zero. The estimator is obtained by an iterative reweighting approach. Each sample point is assigned a weight that is iteratively updated by solving a convex optimization problem. We also establish a dimension-free non-asymptotic risk bound for the expected error of the proposed estimator. It is the first result of this kind in the literature and involves only the effective rank of the covariance matrix. Finally, we show that the obtained results can be extended to sub-Gaussian distributions, as well as to the cases of unknown rate of contamination or unknown covariance matrix.
Recommendations
- Robust sub-Gaussian estimation of a mean vector in nearly linear time
- Robustly learning a Gaussian: getting optimal error, efficiently
- Excess-risk consistency of group-hard thresholding estimator in robust estimation of Gaussian mean
- Nearly optimal robust mean estimation via empirical characteristic function
- Robust multivariate mean estimation: the optimality of trimmed mean
Cites work
- A general decision theory for Huber's \(\epsilon\)-contamination model
- A geometric analysis of subspace clustering with outliers
- Adaptive robust estimation in sparse vector model
- Asymptotically Minimax Adaptive Estimation. I: Upper Bounds. Optimally Adaptive Estimates
- Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
- Breakdown points of affine equivariant estimators of multivariate location and covariance matrices
- Breakdown properties of location estimates based on halfspace depth and projected outlyingness
- Classification with imperfect training labels
- Concentration inequalities and moment bounds for sample covariance operators
- Confidence regions and minimax rates in outlier-robust estimation on the probability simplex
- Dual subgradient algorithms for large-scale nonsmooth learning problems
- ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
- High-dimensional robust mean estimation in nearly-linear time
- scientific article; zbMATH DE number 3842984 (Why is no real title available?)
- scientific article; zbMATH DE number 3829050 (Why is no real title available?)
- scientific article; zbMATH DE number 3986407 (Why is no real title available?)
- Learning from MOM's principles: Le Cam's approach
- Least Median of Squares Regression
- Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
- Near-optimal mean estimators with respect to general norms
- Optimal pointwise adaptive methods in nonparametric estimation
- Risk minimization by median-of-means tournaments
- Robust and computationally feasible community detection in the presence of arbitrary outlier nodes
- Robust covariance and scatter matrix estimation under Huber's contamination model
- Robust estimators in high-dimensions without the computational intractability
- Robust low-rank matrix estimation
- Robust machine learning by median-of-means: theory and practice
- Robust matrix completion
- Robust multivariate mean estimation: the optimality of trimmed mean
- Robust regression via mutivariate regression depth
- Robust Statistics
- Robust Statistics
- Robust sub-Gaussian estimation of a mean vector in nearly linear time
- Robustly learning a Gaussian: getting optimal error, efficiently
- Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
- Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
- Sub-Gaussian mean estimators
- Tight conditions for consistency of variable selection in the context of high dimensionality
Cited in
(23)- Robust dimension-free Gram operator estimates
- Nearly optimal robust mean estimation via empirical characteristic function
- Robust sub-Gaussian estimation of a mean vector in nearly linear time
- Concentration study of M-estimators using the influence function
- Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
- Confidence regions and minimax rates in outlier-robust estimation on the probability simplex
- Excess-risk consistency of group-hard thresholding estimator in robust estimation of Gaussian mean
- Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
- Robust multivariate mean estimation: the optimality of trimmed mean
- Robustly learning a Gaussian: getting optimal error, efficiently
- Robust estimators in high-dimensions without the computational intractability
- Robust W-GAN-based estimation under Wasserstein contamination
- Non-asymptotic analysis and inference for an outlyingness induced winsorized mean
- Re-thinking high-dimensional mathematical statistics. Abstracts from the workshop held May 15--21, 2022
- Information theoretic limits of robust sub-Gaussian mean estimation under star-shaped constraints
- Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction
- Statistically optimal robust mean and covariance estimation for anisotropic gaussians
- Outlier robust and sparse estimation of linear regression coefficients
- Sharp optimality of sparse group LASSO and SLOPE under weaker assumptions
- Adaptive robust confidence intervals
- Estimation beyond missing (completely) at random
- Location and scatter halfspace median under α -symmetric distributions
- Winsorized mean estimation with heavy tails and adversarial contamination
This page was built for publication: All-in-one robust estimator of the Gaussian mean
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2131271)
