Local greedy approximation for nonlinear regression and neural network training.

DOI10.1214/aos/1015957398zbMath1105.62354OpenAlexW1576937288MaRDI QIDQ1848831

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

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

Related Items (1)

Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm

Cites Work

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

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