Optimal convergence rates of deep neural networks in a classification setting

DOI10.1214/23-ejs2187arXiv2207.12180MaRDI QIDQ6184926

Joseph T. Meyer

Publication date: 5 January 2024

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2207.12180

zbMATH Keywords

classificationTsybakov noise conditiondeep neural networks

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Minimax procedures in statistical decision theory (62C20)

Cites Work

• Fast learning rates for plug-in classifiers
• Approximation and estimation bounds for artificial neural networks
• Smooth discrimination analysis
• Optimal aggregation of classifiers in statistical learning.
• On the rate of convergence of fully connected deep neural network regression estimates
• Convergence rates of deep ReLU networks for multiclass classification
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Nonparametric regression using deep neural networks with ReLU activation function
• Metric entropy of some classes of sets with differentiable boundaries
• Error bounds for approximations with deep ReLU networks
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Estimation of a Function of Low Local Dimensionality by Deep Neural Networks
• Approximation by superpositions of a sigmoidal function
• Fast convergence rates of deep neural networks for classification

This page was built for publication: Optimal convergence rates of deep neural networks in a classification setting