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

DOI10.1016/j.jat.2006.03.016zbMath1106.41024OpenAlexW2016220370MaRDI QIDQ863343

Andreas Hofinger

Publication date: 26 January 2007

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jat.2006.03.016

zbMATH Keywords

regularizationgreedy algorithmadaptivedata noise

Mathematics Subject Classification ID

Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (2)

The weight-decay technique in learning from data: an optimization point of view ⋮ Learning a function from noisy samples at a finite sparse set of points

Cites Work

• Unnamed Item
• Unnamed Item
• Learning a function from noisy samples at a finite sparse set of points
• 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
• Generalization bounds for function approximation from scattered noisy data
• Rates of convex approximation in non-Hilbert spaces
• Nonlinear methods of approximation
• Regularized greedy algorithms for network training with data noise
• Optimal nonlinear approximation
• Local greedy approximation for nonlinear regression and neural network training.
• Some remarks on greedy algorithms
• Weak greedy algorithms
• On the mathematical foundations of learning
• Remarks on projection pursuit regression and density estimation
• Universal approximation bounds for superpositions of a sigmoidal function
• Efficient agnostic learning of neural networks with bounded fan-in
• Regularized data-driven construction of fuzzy controllers
• Shannon sampling and function reconstruction from point values
• Error bounds for approximation with neural networks

This page was built for publication: Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm