Minimax rates of convergence for nonparametric location-scale models

TL;DR

This paper establishes the minimax convergence rates for nonparametric location-scale models, including various regression types, under mild conditions, with implications for different error distributions and model applications.

Contribution

It derives the minimax rates of convergence for nonparametric location-scale models based on metric entropy, extending understanding across multiple error distributions and model structures.

Findings

Minimax rates depend on the metric entropy of the function class.

Rates are established for diverse error distributions including asymmetric Laplace and Cauchy.

Applications include low order interaction and multiple index models.

Abstract

This paper studies minimax rates of convergence for nonparametric location-scale models, which include mean, quantile and expectile regression settings. Under Hellinger differentiability on the error distribution and other mild conditions, we show that the minimax rate of convergence for estimating the regression function under the squared $L_2$ loss is determined by the metric entropy of the nonparametric function class. Different error distributions, including asymmetric Laplace distribution, asymmetric connected double truncated gamma distribution, connected normal-Laplace distribution, Cauchy distribution and asymmetric normal distribution are studied as examples. Applications on low order interaction models and multiple index models are also given.