Derivative-free optimization and neural networks for robust regression

Beliakov, Gleb, Kelarev, Andrei and Yearwood, John 2012, Derivative-free optimization and neural networks for robust regression, Optimization, vol. 61, no. 12, pp. 1467-1490.

Attached Files
Name Description MIMEType Size Downloads

Title Derivative-free optimization and neural networks for robust regression
Author(s) Beliakov, Gleb
Kelarev, Andrei
Yearwood, John
Journal name Optimization
Volume number 61
Issue number 12
Start page 1467
End page 1490
Total pages 24
Publisher Taylor & Francis
Place of publication Abingdon, England
Publication date 2012
ISSN 0233-1934
1029-4945
Keyword(s) global optimization
least-trimmed squares
neural networks
non-smooth optimization
robust regression
Summary 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.
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category C1 Refereed article in a scholarly journal
Copyright notice ©2012, Taylor & Francis
Persistent URL http://hdl.handle.net/10536/DRO/DU:30051386

Document type: Journal Article
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 50 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Mon, 18 Mar 2013, 10:19:16 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.