Rate-optimal estimation for a general class of nonparametric regression models with unknown link functions

DOI10.1214/009053607000000415MaRDI QIDQ2473076zbMATH OpenOpenAlexFDO

Authors Joel Horowitz, Enno Mammen

Publication date 26 February 2008

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

Full work available at URL https://arxiv.org/abs/0803.2999, https://projecteuclid.org/euclid.aos/1201012973

zbMATH Keywords

generalized additive modelspenalized least squaressmoothing splinesempirical process methodsmultivariate curve estimation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Neural nets and related approaches to inference from stochastic processes (62M45)

Abstract: This paper discusses a nonparametric regression model that naturally generalizes neural network models. The model is based on a finite number of one-dimensional transformations and can be estimated with a one-dimensional rate of convergence. The model contains the generalized additive model with unknown link function as a special case. For this case, it is shown that the additive components and link function can be estimated with the optimal rate by a smoothing spline that is the solution of a penalized least squares criterion.

Recommendations

• Optimal estimation in additive regression models
• Oracle-efficient nonparametric estimation of an additive model with an unknown link function
• Nonparametric estimation of an additive model with a link function
• Spline smoothing and optimal rates of convergence in nonparametric regression models
• Estimating a regression function

Cites work

• scientific article; zbMATH DE number 46694 (Why is no real title available?)
• scientific article; zbMATH DE number 47282 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 3458075 (Why is no real title available?)
• scientific article; zbMATH DE number 3491650 (Why is no real title available?)
• scientific article; zbMATH DE number 3525575 (Why is no real title available?)
• scientific article; zbMATH DE number 3449248 (Why is no real title available?)
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• scientific article; zbMATH DE number 3229907 (Why is no real title available?)
• A kernel method of estimating structured nonparametric regression based on marginal integration
• A simple smooth backfitting method for additive models
• Additive regression and other nonparametric models
• Asymptotic properties of backfitting estimators
• BOOTSTRAP INFERENCE IN SEMIPARAMETRIC GENERALIZED ADDITIVE MODELS
• Bandwidth selection for smooth backfitting in additive models
• Convergence rates and asymptotic normality for series estimators
• Direct estimation of low-dimensional components in additive models.
• EFFICIENT ESTIMATION OF GENERALIZED ADDITIVE NONPARAMETRIC REGRESSION MODELS
• Estimating Optimal Transformations for Multiple Regression and Correlation
• Estimating a regression function
• Estimation of additive regression models with known links
• Fitting a bivariate additive model by local polynomial regression
• Generalised structured models
• Linear smoothers and additive models
• Local Likelihood Estimation in Generalized Additive Models
• Local Partitioned Regression
• Nonparametric Estimation of a Generalized Additive Model With an Unknown Link Function
• Nonparametric Identification of Nonlinear Time Series: Projections
• Nonparametric estimation of an additive model with a link function
• Nonparametric estimation of composite functions
• On Kolmogorov's representation of functions of several variables by functions of one variable
• Optimal estimation in additive regression models
• Penalized quasi-likelihood estimation in partial linear models
• Semiparametric least squares (SLS) and weighted SLS estimation of single-index models
• Smooth Backfitting in Practice
• Smooth backfitting in generalized additive models
• Smoothing Splines and Shape Restrictions
• The dimensionality reduction principle for generalized additive models
• The existence and asymptotic properties of a backfitting projection algorithm under weak conditions
• The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)

Cited in

(33)

• Statistical inference in sparse high-dimensional additive models
• Nonparametric regression using deep neural networks with ReLU activation function
• Analysis of the rate of convergence of fully connected deep neural network regression estimates with smooth activation function
• Convergence rates of deep ReLU networks for multiclass classification
• Identification and estimation in quantile varying-coefficient models with unknown link function
• NONPARAMETRIC ESTIMATION OF GENERALIZED TRANSFORMATION MODELS WITH FIXED EFFECTS
• Non-parametric regression tests using dimension reduction techniques
• Deep learning for the partially linear Cox model
• Specification testing for transformation models with an application to generalized accelerated failure-time models
• Robust nonparametric regression based on deep ReLU neural networks
• Structural adaptive deconvolution under \({\mathbb{L}_p}\)-losses
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Adaptive estimation over anisotropic functional classes via oracle approach
• Nonparametric estimation of noisy integral equations of the second kind
• Statistical inference for time-changed Lévy processes via composite characteristic function estimation
• Efficient estimation and computation for the generalised additive models with unknown link function
• Estimating composite functions by model selection
• The Kolmogorov-Arnold representation theorem revisited
• Estimation and Calibration of Lévy Models via Fourier Methods
• On the rate of convergence of fully connected deep neural network regression estimates
• Very high dimensional semiparametric models. Abstracts from the workshop held October 2--8, 2011.
• Analysis of the rate of convergence of two regression estimates defined by neural features which are easy to implement
• Estimating a regression function in exponential families by model selection
• \(\mathbb{L}_{p}\) adaptive estimation of an anisotropic density under independence hypothesis
• Optimal sup-norm rates and uniform inference on nonlinear functionals of nonparametric IV regression
• A multiplex interdependent durations model
• Multivariate intensity estimation via hyperbolic wavelet selection
• Estimation in additive models with fixed censored responses
• Structural adaptation in the density model
• Oracle-efficient nonparametric estimation of an additive model with an unknown link function
• Nonparametric estimation of composite functions
• Identification and estimation of local average derivatives in non-separable models without monotonicity
• Generalised additive dependency inflated models including aggregated covariates

This page was built for publication: Rate-optimal estimation for a general class of nonparametric regression models with unknown link functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2473076)