23
0

Mean Estimation in Banach Spaces Under Infinite Variance and 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 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 ppth moment for some p>1p > 1. In particular, our results hold for 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 2-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 nn, and non-asymptotic law of the iterated logarithm type inequalities, which match the tightness of line-crossing inequalities at all points in time up to a doubly logarithmic factor in nn. 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.

View on arXiv
Comments on this paper