Rademacher complexity and the generalization error of residual networks

DOI10.4310/CMS.2020.v18.n6.a10zbMath1467.62158OpenAlexW3095482116MaRDI QIDQ2023508

Chao Ma, Qingcan Wang, E. Weinan

Publication date: 3 May 2021

Published in: Communications in Mathematical Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.4310/cms.2020.v18.n6.a10

zbMATH Keywords

residual network\textit{a priori} estimateweighted path norm

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) General nonlinear regression (62J02) Multidimensional problems (41A63) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (3)

Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks ⋮ A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations ⋮ A mathematical perspective of machine learning

This page was built for publication: Rademacher complexity and the generalization error of residual networks