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

TL;DR

This paper introduces a unified framework for high-dimensional mean estimation under adversarial corruption or heavy tails, simplifying algorithms and improving runtime by connecting robust statistics with regret minimization.

Contribution

It presents a duality theorem and a meta-problem that unify robust and heavy-tailed mean estimation, leading to simpler, more efficient algorithms with improved analysis.

Findings

Unified view simplifies robust and heavy-tailed mean estimation

Algorithms achieve optimal or near-optimal performance

Runtime matches the fastest known algorithms in the field

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. In this paper, we provide a meta-problem and a duality theorem that lead to a new unified view on robust and heavy-tailed mean estimation in high dimensions. We show that the meta-problem can be solved either by a variant of the Filter algorithm from the recent literature on robust estimation or by the quantum entropy scoring scheme (QUE), due to Dong, Hopkins and Li (NeurIPS '19). By leveraging our duality theorem, these results translate into simple and efficient algorithms for both robust and heavy-tailed settings. Furthermore, the QUE-based procedure has run-time that matches the fastest known algorithms on both fronts. Our analysis of Filter is through the classic regret bound of the multiplicative weights update method. This connection allows us to avoid the technical complications in previous works and improve upon the run-time analysis of a gradient-descent-based algorithm for robust mean estimation by Cheng, Diakonikolas, Ge and Soltanolkotabi (ICML '20).