A SIMPLE LEMMA ON GREEDY APPROXIMATION IN HILBERT-SPACE AND CONVERGENCE-RATES FOR PROJECTION PURSUIT REGRESSION AND NEURAL NETWORK TRAINING

被引：290

作者：

JONES, LK ^{[1
]}

机构：

[1] UNIV MASSACHUSETTS,DEPT MATH,LOWELL,MA 01854

来源：

ANNALS OF STATISTICS | 1992年 / 20卷 / 01期

关键词：

PROJECTION PURSUIT; GREEDY EXPANSION; NEURAL NETWORK;

D O I：

10.1214/aos/1176348546

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

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/ square-root 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.

引用

页码：608 / 613

页数：6

共 6 条

[1]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[2] PROJECTION-BASED APPROXIMATION AND A DUALITY WITH KERNEL METHODS [J].