Score: 0

Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means

Published: June 17, 2025 | arXiv ID: 2506.14673v3

By: Mikael Møller Høgsgaard, Andrea Paudice

Potential Business Impact:

Finds averages in tricky data better.

Business Areas:
A/B Testing Data and Analytics

The Median of Means (MoM) is a mean estimator that has gained popularity in the context of heavy-tailed data. In this work, we analyze its performance in the task of simultaneously estimating the mean of each function in a class $\mathcal{F}$ when the data distribution possesses only the first $p$ moments for $p \in (1,2]$. We prove a new sample complexity bound using a novel symmetrization technique that may be of independent interest. Additionally, we present applications of our result to $k$-means clustering with unbounded inputs and linear regression with general losses, improving upon existing works.

Page Count
32 pages

Category
Statistics:
Machine Learning (Stat)