All-In-One Robust Estimator of the Gaussian Mean

02/04/2020
by   Arnak S. Dalalyan, et al.
0

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 and orthogonal transformations. Third, it has a high breakdown point equal to 0.5, and a nearly-minimax-rate-breakdown point approximately equal to 0.28. Fourth, it is minimax rate optimal when data consist of independent observations corrupted by adversarially chosen outliers. Fifth, it is asymptotically optimal 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 using 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 of this kind results in the literature and involves only the effective rank of the covariance matrix.

READ FULL TEXT

page 6

page 7

research
04/05/2022

Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction

We study the problem of robust estimation of the mean vector of a sub-Ga...
research
04/09/2021

Concentration study of M-estimators using the influence function

We present a new finite-sample analysis of M-estimators of locations in ...
research
01/23/2019

Optimal Uncertainty Size in Distributionally Robust Inverse Covariance Estimation

In a recent paper, Nguyen, Kuhn, and Esfahani (2018) built a distributio...
research
12/15/2017

Rate-optimal estimation of p-dimensional linear functionals in a sparse Gaussian model

We consider two problems of estimation in high-dimensional Gaussian mode...
research
01/31/2020

Rigorous Guarantees for Tyler's M-estimator via quantum expansion

Estimating the shape of an elliptical distribution is a fundamental prob...
research
11/05/2019

A Fourier Analytical Approach to Estimation of Smooth Functions in Gaussian Shift Model

We study the estimation of f() under Gaussian shift model = +, where ∈^d...
research
02/01/2021

Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms

We consider the problem of robust mean and location estimation w.r.t. an...

Please sign up or login with your details

Forgot password? Click here to reset