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

DOI10.1214/19-AOS1915MaRDI QIDQ2215716zbMATH OpenOpenAlexFDO

Authors Ohad Shamir

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/1597370656

zbMATH Keywords

additive modelsminimax estimation riskmultilayer neural networksnonparametric regressionrectified linear activation functionrectified linear unit (ReLU)

Mathematics Subject Classification ID

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

Cites work

• Boosting the margin: a new explanation for the effectiveness of voting methods
• Distribution-specific hardness of learning neural networks
• Neural Network Learning
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Stochastic subgradient method converges on tame functions
• The implicit bias of gradient descent on separable data
• The landscape of empirical risk for nonconvex losses

Cited in

(3)

• Statistical theory for image classification using deep convolutional neural network with cross-entropy loss under the hierarchical max-pooling model
• Learning time-scales in two-layers neural networks
• Operator theory, kernels, and feedforward neural networks

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215716)