Rejoinder: ``Nonparametric regression using deep neural networks with ReLU activation function

DOI10.1214/19-AOS1931zbMath1455.62086OpenAlexW3049059782MaRDI QIDQ2215717

Johannes Schmidt-Hieber

Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aos/1597370657

zbMATH Keywords

additive modelsnonparametric regressionmultilayer neural networksrectified linear unit (ReLU)minimax estimation riskrectified linear activation function

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Minimax procedures in statistical decision theory (62C20) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (3)

A Deep Generative Approach to Conditional Sampling ⋮ Universal regular conditional distributions via probabilistic transformers ⋮ Over-parametrized deep neural networks minimizing the empirical risk do not generalize well

Cites Work

• Unnamed Item
• Unnamed Item
• A randomized Kaczmarz algorithm with exponential convergence
• Minimax or maxisets?
• Randomized Iterative Methods for Linear Systems

This page was built for publication: Rejoinder: ``Nonparametric regression using deep neural networks with ReLU activation function