Local greedy approximation for nonlinear regression and neural network training.

DOI10.1214/AOS/1015957398MaRDI QIDQ1848831zbMATH OpenOpenAlexFDO

Authors Lee Kenneth Jones

Publication date 14 November 2002

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

Full work available at URL https://doi.org/10.1214/aos/1015957398

Mathematics Subject Classification ID

General nonlinear regression (62J02) Estimation in multivariate analysis (62H12) Neural nets and related approaches to inference from stochastic processes (62M45)

Recommendations

• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Local approximation on artificial neural networks
• scientific article; zbMATH DE number 952763
• Regularized greedy algorithms for network training with data noise
• Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm

Cites work

• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Efficient agnostic learning of neural networks with bounded fan-in
• Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data
• Greedy function approximation: A gradient boosting machine.
• On a conjecture of Huber concerning the convergence of projection pursuit regression
• On the infeasibility of training neural networks with small mean-squared error
• Projection pursuit
• Rates of convex approximation in non-Hilbert spaces
• Remarks on projection pursuit regression and density estimation
• Some remarks on greedy algorithms
• The computational intractability of training sigmoidal neural networks
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(4)

• Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm
• Nonparametric nonlinear regression using polynomial and neural approximators: a numerical comparison
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Greedy training algorithms for neural networks and applications to PDEs

This page was built for publication: Local greedy approximation for nonlinear regression and neural network training.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1848831)