Extending the scope of the small-ball method

TL;DR

This paper broadens the small-ball method to provide almost-isometric bounds on quadratic empirical processes without requiring uniform small-ball conditions, and introduces stability under majority voting.

Contribution

It extends the small-ball method to achieve almost-isometric bounds and removes the need for uniform small-ball assumptions, enhancing its applicability.

Findings

Achieves high probability, almost-isometric lower bounds.

Removes the need for uniform small-ball conditions.

Ensures stability under majority voting.

Abstract

The small-ball method was introduced as a way of obtaining a high probability, isomorphic lower bound on the quadratic empirical process, under weak assumptions on the indexing class. The key assumption was that class members satisfy a uniform small-ball estimate: that $Pr(|f| \geq \kappa\|f\|_{L_2}) \geq \delta$ for given constants $\kappa$ and $\delta$. Here we extend the small-ball method and obtain a high probability, almost-isometric (rather than isomorphic) lower bound on the quadratic empirical process. The scope of the result is considerably wider than the small-ball method: there is no need for class members to satisfy a uniform small-ball condition, and moreover, motivated by the notion of tournament learning procedures, the result is stable under a `majority vote'.