Derivative-free optimization and neural networks for robust regression

- Beliakov, Gleb, Kelarev, Andrei, Yearwood, John

Title
Derivative-free optimization and neural networks for robust regression
Creator
Beliakov, Gleb; Kelarev, Andrei; Yearwood, John
Date
2012
Type
Text; Journal article
Identifier
http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/60541
Identifier
vital:4807
Identifier
https://doi.org/10.1080/02331934.2012.674946
Identifier
ISSN:0233-1934
Abstract
Large outliers break down linear and nonlinear regression models. Robust regression methods allow one to filter out the outliers when building a model. By replacing the traditional least squares criterion with the least trimmed squares (LTS) criterion, in which half of data is treated as potential outliers, one can fit accurate regression models to strongly contaminated data. High-breakdown methods have become very well established in linear regression, but have started being applied for non-linear regression only recently. In this work, we examine the problem of fitting artificial neural networks (ANNs) to contaminated data using LTS criterion. We introduce a penalized LTS criterion which prevents unnecessary removal of valid data. Training of ANNs leads to a challenging non-smooth global optimization problem. We compare the efficiency of several derivative-free optimization methods in solving it, and show that our approach identifies the outliers correctly when ANNs are used for nonlinear regression. © 2012 Copyright Taylor and Francis Group, LLC.
Relation
Optimization Vol. 61, no. 12 (2012), p. 1467-1490
Rights
Copyright 2012 Taylor and Francis Group, LLC
Rights
Open Access
Rights
This metadata is freely available under a CCO license
Subject
Global optimization; Least-trimmed squares; Neural networks; Non-smooth optimization; Robust regression
Full Text
Reviewed
  • Hits: 1942
  • Visitors: 2213
  • Downloads: 216
Thumbnail File Description Size Format
SOURCE1 Accepted version 708 KB Adobe Acrobat PDF