Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ko, Hyunouk, Huo, Xiaoming
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916110819917824
author Ko, Hyunouk
Huo, Xiaoming
author_facet Ko, Hyunouk
Huo, Xiaoming
contents In this paper, we prove the universal consistency of wide and deep ReLU neural network classifiers trained on the logistic loss. We also give sufficient conditions for a class of probability measures for which classifiers based on neural networks achieve minimax optimal rates of convergence. The result applies to a wide range of known function classes. In particular, while most previous works impose explicit smoothness assumptions on the regression function, our framework encompasses more general settings. The proposed neural networks are either the minimizers of the logistic loss or the $0$-$1$ loss. In the former case, they are interpolating classifiers that exhibit a benign overfitting behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04286
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Ko, Hyunouk
Huo, Xiaoming
Machine Learning
In this paper, we prove the universal consistency of wide and deep ReLU neural network classifiers trained on the logistic loss. We also give sufficient conditions for a class of probability measures for which classifiers based on neural networks achieve minimax optimal rates of convergence. The result applies to a wide range of known function classes. In particular, while most previous works impose explicit smoothness assumptions on the regression function, our framework encompasses more general settings. The proposed neural networks are either the minimizers of the logistic loss or the $0$-$1$ loss. In the former case, they are interpolating classifiers that exhibit a benign overfitting behavior.
title Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
topic Machine Learning
url https://arxiv.org/abs/2401.04286