English

Near-optimal mean estimators with respect to general norms

Statistics Theory 2018-06-19 v1 Statistics Theory

Abstract

We study the problem of estimating the mean of a random vector in Rd\mathbb{R}^d based on an i.i.d.\ sample, when the accuracy of the estimator is measured by a general norm on Rd\mathbb{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.

Keywords

Cite

@article{arxiv.1806.06233,
  title  = {Near-optimal mean estimators with respect to general norms},
  author = {Gábor Lugosi and Shahar Mendelson},
  journal= {arXiv preprint arXiv:1806.06233},
  year   = {2018}
}