Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
Abstract
We study the problem of estimating the mean of a distribution in high dimensions when either the samples are adversarially corrupted or the distribution is heavy-tailed. Recent developments in robust statistics have established efficient and (near) optimal procedures for both settings. However, the algorithms developed on each side tend to be sophisticated and do not directly transfer to the other, with many of them having ad-hoc or complicated analyses.
Cite
Text
Hopkins et al. "Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization." Neural Information Processing Systems, 2020.Markdown
[Hopkins et al. "Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/hopkins2020neurips-robust/)BibTeX
@inproceedings{hopkins2020neurips-robust,
title = {{Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization}},
author = {Hopkins, Sam and Li, Jerry and Zhang, Fred},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/hopkins2020neurips-robust/}
}