Mean Estimation in Banach Spaces Under Infinite Variance and Martingale Dependence

TL;DR

This paper develops robust mean estimators for Banach space-valued heavy-tailed data with infinite variance, providing tight, dimension-free concentration bounds under martingale dependence.

Contribution

It extends truncation-based mean estimation to cases with only bounded p-th moments, handling infinite variance and martingale dependence in Banach spaces.

Findings

Provides time-uniform concentration inequalities for the estimator.

Handles distributions with infinite variance.

Results are dimension-free and applicable under martingale dependence.

Abstract

We consider estimating the shared mean of a sequence of heavy-tailed random variables taking values in a Banach space. In particular, we revisit and extend a simple truncation-based mean estimator first proposed by Catoni and Giulini. While existing truncation-based approaches require a bound on the raw (non-central) second moment of observations, our results hold under a bound on either the central or non-central $p$th moment for some $p \in (1,2]$. Our analysis thus handles distributions with infinite variance. The main contributions of the paper follow from exploiting connections between truncation-based mean estimation and the concentration of martingales in smooth Banach spaces. We prove two types of time-uniform bounds on the distance between the estimator and unknown mean: line-crossing inequalities, which can be optimized for a fixed sample size $n$, and iterated logarithm inequalities, which match the tightness of line-crossing inequalities at all points in time up to a doubly logarithmic factor in $n$. Our results do not depend on the dimension of the Banach space, hold under martingale dependence, and all constants in the inequalities are known and small.