Nonasymptotic Bounds on the L
2 Error of Neural Network Regression Estimates |
| |
Authors: | Michael Hamers Michael Kohler |
| |
Institution: | 1. Fachbereich Mathematik, Universit?t Stuttgart, Pfaffenwaldring 57, D-70569, Stuttgart, Germany 2. Fachrichtung Mathematik, Universit?t des Saarlandes, Postfach 151150, D-66041, Saarbrücken, Germany
|
| |
Abstract: | The estimation of multivariate regression functions from bounded i.i.d. data is considered. The L
2 error with integration with respect to the design measure is used as an error criterion. The distribution of the design is
assumed to be concentrated on a finite set. Neural network estimates are defined by minimizing the empirical L
2 risk over various sets of feedforward neural networks. Nonasymptotic bounds on the L
2 error of these estimates are presented. The results imply that neural networks are able to adapt to additive regression functions
and to regression functions which are a sum of ridge functions, and hence are able to circumvent the curse of dimensionality
in these cases. |
| |
Keywords: | Neural networks Nonparametric regression Dimension reduction Additive models Curse of dimensionality |
本文献已被 SpringerLink 等数据库收录! |
|