Uniform mean estimation via generic chaining

TL;DR

This paper introduces an optimal uniform mean estimator using generic chaining, providing high-probability bounds that improve understanding of high-dimensional probability and statistics.

Contribution

It combines Talagrand's generic chaining with optimal mean estimation to create a new estimator with strong uniform guarantees under minimal assumptions.

Findings

Provides a high-probability bound for the estimator's uniform deviation

Shows the estimator's effectiveness in high-dimensional probability

Connects generic chaining with mean estimation techniques

Abstract

We introduce an empirical functional $\Psi$ that is an optimal uniform mean estimator: Let $F\subset L_2(\mu)$ be a class of mean zero functions, $u$ is a real valued function, and $X_1,\dots,X_N$ are independent, distributed according to $\mu$. We show that under minimal assumptions, with $\mu^{\otimes N}$ exponentially high probability, \[ \sup_{f\in F} |\Psi(X_1,\dots,X_N,f) - \mathbb{E} u(f(X))| \leq c R(F) \frac{ \mathbb{E} \sup_{f\in F } |G_f| }{\sqrt N}, \] where $(G_f)_{f\in F}$ is the gaussian processes indexed by $F$ and $R(F)$ is an appropriate notion of `diameter' of the class $\{u(f(X)) : f\in F\}$. The fact that such a bound is possible is surprising, and it leads to the solution of various key problems in high dimensional probability and high dimensional statistics. The construction is based on combining Talagrand's generic chaining mechanism with optimal mean estimation procedures for a single real-valued random variable.