Near-optimal mean estimators with respect to general norms

2018/06/16 by Lugosi, Gábor, Mendelson, Shahar · 1 citation
#FOS: Mathematics #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1806.06233

Abstract

We study the problem of estimating the mean of a random vector in ℝ^d based on an i.i.d. sample, when the accuracy of the estimator is measured by a general norm on ℝ^d. We construct an estimator (that depends on the norm) that achieves an essentially optimal accuracy/confidence tradeoff under the only assumption that the random vector has a well-defined covariance matrix. The estimator is based on the construction of a uniform median-of-means estimator in a class of real valued functions that may be of independent interest.

Cited by

• Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means

Related

• Multivariate mean estimation with direction-dependent accuracy
• Robust multivariate mean estimation: the optimality of trimmed mean
• Sub-Gaussian estimators of the mean of a random vector
• Dimension-free PAC-Bayesian bounds for the estimation of the mean of a random vector
• Nearly Optimal Robust Mean Estimation via Empirical Characteristic Function