Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization

Sam Hopkins; Jerry Li; Fred Zhang

NeurIPS 2020poster86 citations

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.

BibTeX

@inproceedings{NEURIPS2020_8a1276c2,
 author = {Hopkins, Sam and Li, Jerry and Zhang, Fred},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {11902--11912},
 publisher = {Curran Associates, Inc.},
 title = {Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/8a1276c25f5efe85f0fc4020fbf5b4f8-Paper.pdf},
 volume = {33},
 year = {2020}
}