Nonasymptotic bounds on the \(L_{2}\) error of neural network regression estimates

DOI10.1007/s10463-005-0005-9zbMath1095.62113OpenAlexW2135462575MaRDI QIDQ2502135

Michael Kohler, Michael Hamers

Publication date: 12 September 2006

Published in: Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10463-005-0005-9

zbMATH Keywords

Neural networksAdditive modelsDimension reductionCurse of dimensionality

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (5)

Estimates on compressed neural networks regression ⋮ Analysis of convergence performance of neural networks ranking algorithm ⋮ Nonparametric regression using deep neural networks with ReLU activation function ⋮ Optimal nonparametric inference via deep neural network ⋮ Analysis of the rate of convergence of least squares neural network regression estimates in case of measurement errors

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Additive regression and other nonparametric models
• Interaction spline models and their convergence rates
• Approximation and estimation bounds for artificial neural networks
• The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
• A bound on the expected maximal deviation of averages from their means.
• Multilayer feedforward networks are universal approximators
• Projection estimation in multiple regression with application to functional ANOVA models
• Optimal global rates of convergence for nonparametric regression
• A distribution-free theory of nonparametric regression
• How well can a regression function be estimated if the distribution of the (random) design is concentrated on a finite set?
• Smoothing spline ANOVA for exponential families, with application to the Wisconsin epidemiological study of diabetic retinopathy. (The 1994 Neyman Memorial Lecture)
• Estimation of generalized additive models
• Fitting additive models to regression data. Diagnostics and alternative views
• Estimating Optimal Transformations for Multiple Regression and Correlation
• Estimation of additive regression models with known links
• Miscellanea. Efficient estimation of additive nonparametric regression models
• Nonparametric estimation via empirical risk minimization
• A kernel method of estimating structured nonparametric regression based on marginal integration
• Asymptotic distribution of the errors in scalar and vector quantizers
• Neural Network Learning
• A logical calculus of the ideas immanent in nervous activity
• Convergence of stochastic processes
• Approximation by superpositions of a sigmoidal function
• Nonparametric regression function estimation using interaction least squares splines and complexity regularization.

This page was built for publication: Nonasymptotic bounds on the \(L_{2}\) error of neural network regression estimates