Global resolution of the support vector machine regression parameters selection problem with LPCC

Support vector machine regression is a robust data fitting method to minimize the sum of deducted residuals of regression, and thus is less sensitive to changes of data near the regression hyperplane. Two design parameters, the insensitive tube size (εe) and the weight assigned to the regression err...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu-Ching Lee, Jong-Shi Pang, JohnE. Mitchell
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2015
Materias:	90C26 Applied mathematics. Quantitative methods T57-57.97 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/12eb93a85e024a6791ee2a350bf105c4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:12eb93a85e024a6791ee2a350bf105c4
record_format	dspace
spelling	oai:doaj.org-article:12eb93a85e024a6791ee2a350bf105c42021-12-02T05:00:45ZGlobal resolution of the support vector machine regression parameters selection problem with LPCC2192-440610.1007/s13675-015-0041-zhttps://doaj.org/article/12eb93a85e024a6791ee2a350bf105c42015-09-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2192440621000460https://doaj.org/toc/2192-4406Support vector machine regression is a robust data fitting method to minimize the sum of deducted residuals of regression, and thus is less sensitive to changes of data near the regression hyperplane. Two design parameters, the insensitive tube size (εe) and the weight assigned to the regression error trading off the normed support vector (Ce), are selected by user to gain better forecasts. The global training and validation parameter selection procedure for the support vector machine regression can be formulated as a bi-level optimization model, which is equivalently reformulated as linear program with linear complementarity constraints (LPCC). We propose a rectangle search global optimization algorithm to solve this LPCC. The algorithm exhausts the invariancy regions on the parameter plane ((Ce,εe)-plane) without explicitly identifying the edges of the regions. This algorithm is tested on synthetic and real-world support vector machine regression problems with up to hundreds of data points, and the efficiency are compared with several approaches. The obtained global optimal parameter is an important benchmark for every other selection of parameters.Yu-Ching LeeJong-Shi PangJohnE. MitchellElsevierarticle90C26Applied mathematics. Quantitative methodsT57-57.97Electronic computers. Computer scienceQA75.5-76.95ENEURO Journal on Computational Optimization, Vol 3, Iss 3, Pp 197-261 (2015)
institution	DOAJ
collection	DOAJ
language	EN
topic	90C26 Applied mathematics. Quantitative methods T57-57.97 Electronic computers. Computer science QA75.5-76.95
spellingShingle	90C26 Applied mathematics. Quantitative methods T57-57.97 Electronic computers. Computer science QA75.5-76.95 Yu-Ching Lee Jong-Shi Pang JohnE. Mitchell Global resolution of the support vector machine regression parameters selection problem with LPCC
description	Support vector machine regression is a robust data fitting method to minimize the sum of deducted residuals of regression, and thus is less sensitive to changes of data near the regression hyperplane. Two design parameters, the insensitive tube size (εe) and the weight assigned to the regression error trading off the normed support vector (Ce), are selected by user to gain better forecasts. The global training and validation parameter selection procedure for the support vector machine regression can be formulated as a bi-level optimization model, which is equivalently reformulated as linear program with linear complementarity constraints (LPCC). We propose a rectangle search global optimization algorithm to solve this LPCC. The algorithm exhausts the invariancy regions on the parameter plane ((Ce,εe)-plane) without explicitly identifying the edges of the regions. This algorithm is tested on synthetic and real-world support vector machine regression problems with up to hundreds of data points, and the efficiency are compared with several approaches. The obtained global optimal parameter is an important benchmark for every other selection of parameters.
format	article
author	Yu-Ching Lee Jong-Shi Pang JohnE. Mitchell
author_facet	Yu-Ching Lee Jong-Shi Pang JohnE. Mitchell
author_sort	Yu-Ching Lee
title	Global resolution of the support vector machine regression parameters selection problem with LPCC
title_short	Global resolution of the support vector machine regression parameters selection problem with LPCC
title_full	Global resolution of the support vector machine regression parameters selection problem with LPCC
title_fullStr	Global resolution of the support vector machine regression parameters selection problem with LPCC
title_full_unstemmed	Global resolution of the support vector machine regression parameters selection problem with LPCC
title_sort	global resolution of the support vector machine regression parameters selection problem with lpcc
publisher	Elsevier
publishDate	2015
url	https://doaj.org/article/12eb93a85e024a6791ee2a350bf105c4
work_keys_str_mv	AT yuchinglee globalresolutionofthesupportvectormachineregressionparametersselectionproblemwithlpcc AT jongshipang globalresolutionofthesupportvectormachineregressionparametersselectionproblemwithlpcc AT johnemitchell globalresolutionofthesupportvectormachineregressionparametersselectionproblemwithlpcc
_version_	1718400814212448256

Global resolution of the support vector machine regression parameters selection problem with LPCC

Ejemplares similares