How Hard Is Robust Mean Estimation?

03/19/2019
by   Samuel B. Hopkins, et al.
0

Robust mean estimation is the problem of estimating the mean μ∈R^d of a d-dimensional distribution D from a list of independent samples, an ϵ-fraction of which have been arbitrarily corrupted by a malicious adversary. Recent algorithmic progress has resulted in the first polynomial-time algorithms which achieve dimension-independent rates of error: for instance, if D has covariance I, in polynomial-time one may find μ̂ with μ - μ̂≤ O(√(ϵ)). However, error rates achieved by current polynomial-time algorithms, while dimension-independent, are sub-optimal in many natural settings, such as when D is sub-Gaussian, or has bounded 4-th moments. In this work we give worst-case complexity-theoretic evidence that improving on the error rates of current polynomial-time algorithms for robust mean estimation may be computationally intractable in natural settings. We show that several natural approaches to improving error rates of current polynomial-time robust mean estimation algorithms would imply efficient algorithms for the small-set expansion problem, refuting Raghavendra and Steurer's small-set expansion hypothesis (so long as P ≠ NP). We also give the first direct reduction to the robust mean estimation problem, starting from a plausible but nonstandard variant of the small-set expansion problem.

READ FULL TEXT
research
11/23/2018

High-Dimensional Robust Mean Estimation in Nearly-Linear Time

We study the fundamental problem of high-dimensional mean estimation in ...
research
04/12/2017

Robustly Learning a Gaussian: Getting Optimal Error, Efficiently

We study the fundamental problem of learning the parameters of a high-di...
research
02/21/2023

Robust Mean Estimation Without a Mean: Dimension-Independent Error in Polynomial Time for Symmetric Distributions

In this work, we study the problem of robustly estimating the mean/locat...
research
06/11/2019

Faster Algorithms for High-Dimensional Robust Covariance Estimation

We study the problem of estimating the covariance matrix of a high-dimen...
research
04/24/2016

Agnostic Estimation of Mean and Covariance

We consider the problem of estimating the mean and covariance of a distr...
research
05/28/2022

List-Decodable Sparse Mean Estimation

Robust mean estimation is one of the most important problems in statisti...
research
12/23/2019

Algorithms for Heavy-Tailed Statistics: Regression, Covariance Estimation, and Beyond

We study efficient algorithms for linear regression and covariance estim...

Please sign up or login with your details

Forgot password? Click here to reset