Berry-Esseen bounds for Chernoff-type non-standard asymptotics in isotonic regression

TL;DR

This paper establishes Berry-Esseen bounds for Chernoff-type distributions in isotonic regression, providing insights into the accuracy of non-normal approximations in non-regular statistical estimation problems.

Contribution

It introduces novel localization techniques and anti-concentration inequalities to derive Berry-Esseen bounds for Chernoff-type limits in isotonic regression.

Findings

Berry-Esseen bounds match oracle local average estimator performance

Bounds are accurate up to logarithmic factors

Method differs from standard Berry-Esseen techniques

Abstract

A Chernoff-type distribution is a nonnormal distribution defined by the slope at zero of the greatest convex minorant of a two-sided Brownian motion with a polynomial drift. While a Chernoff-type distribution is known to appear as the distributional limit in many non-regular statistical estimation problems, the accuracy of Chernoff-type approximations has remained largely unknown. In the present paper, we tackle this problem and derive Berry-Esseen bounds for Chernoff-type limit distributions in the canonical non-regular statistical estimation problem of isotonic (or monotone) regression. The derived Berry-Esseen bounds match those of the oracle local average estimator with optimal bandwidth in each scenario of possibly different Chernoff-type asymptotics, up to multiplicative logarithmic factors. Our method of proof differs from standard techniques on Berry-Esseen bounds, and relies on new localization techniques in isotonic regression and an anti-concentration inequality for the supremum of a Brownian motion with a Lipschitz drift.