Translator Disclaimer
October2000 Local greedy approximation for nonlinear regression and neural network training
L. K. Jones
Ann. Statist. 28(5): 1379-1389 (October2000). DOI: 10.1214/aos/1015957398

Abstract

A criterion for local estimation and approximation in nonlinear regres- sion and neural network training is introduced and motivated. $N$th-order greedy approximation for the regression (or target) function based on the criterion is shown to converge at rate $O(1/N^{1/2})$ in the nonsampling case.

Citation

Download Citation

L. K. Jones. "Local greedy approximation for nonlinear regression and neural network training." Ann. Statist. 28 (5) 1379 - 1389, October2000. https://doi.org/10.1214/aos/1015957398

Information

Published: October2000
First available in Project Euclid: 12 March 2002

zbMATH: 1105.62354
MathSciNet: MR1805788
Digital Object Identifier: 10.1214/aos/1015957398

Subjects:
Primary: 62H99

Rights: Copyright © 2000 Institute of Mathematical Statistics

JOURNAL ARTICLE
11 PAGES


SHARE
Vol.28 • No. 5 • October2000
Back to Top