English

Efficient median of means estimator

Statistics Theory 2023-05-31 v1 Machine Learning Statistics Theory

Abstract

The goal of this note is to present a modification of the popular median of means estimator that achieves sub-Gaussian deviation bounds with nearly optimal constants under minimal assumptions on the underlying distribution. We build on a recent work on the topic by the author, and prove that desired guarantees can be attained under weaker requirements.

Keywords

Cite

@article{arxiv.2305.18681,
  title  = {Efficient median of means estimator},
  author = {Stanislav Minsker},
  journal= {arXiv preprint arXiv:2305.18681},
  year   = {2023}
}