Open Access
Translator Disclaimer
March, 1992 A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training
Lee K. Jones
Ann. Statist. 20(1): 608-613 (March, 1992). DOI: 10.1214/aos/1176348546

Abstract

A general convergence criterion for certain iterative sequences in Hilbert space is presented. For an important subclass of these sequences, estimates of the rate of convergence are given. Under very mild assumptions these results establish an $O(1/ \sqrt n)$ nonsampling convergence rate for projection pursuit regression and neural network training; where $n$ represents the number of ridge functions, neurons or coefficients in a greedy basis expansion.

Citation

Download Citation

Lee K. Jones. "A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training." Ann. Statist. 20 (1) 608 - 613, March, 1992. https://doi.org/10.1214/aos/1176348546

Information

Published: March, 1992
First available in Project Euclid: 12 April 2007

zbMATH: 0746.62060
MathSciNet: MR1150368
Digital Object Identifier: 10.1214/aos/1176348546

Subjects:
Primary: 62H99

Keywords: greedy expansion , neural network , Projection pursuit

Rights: Copyright © 1992 Institute of Mathematical Statistics

JOURNAL ARTICLE
6 PAGES


SHARE
Vol.20 • No. 1 • March, 1992
Back to Top