Fast Mean Estimation with Sub-Gaussian Rates

Abstract

We propose an estimator for the mean of a random vector in ${\mathbb{R}}^d$ that can be computed in time $O(n^4+n^{2}d)$ for $n$ i.i.d.~samples and that has error bounds matching the sub-Gaussian case. The only assumptions we make about the data distribution are that it has finite mean and covariance; in particular, we make no assumptions about higher-order moments. Like the polynomial time estimator introduced by Hopkins, 2018, which is based on the sum-of-squares hierarchy, our estimator achieves optimal statistical efficiency in this challenging setting, but it has a significantly faster runtime and a simpler analysis.

References in corpus (1)

• Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression

Cited by in corpus (1)

• A Unified Approach to Robust Mean Estimation