期刊名称：Journal of Intelligent Learning Systems and Applications
印刷版ISSN：2150-8402
电子版ISSN：2150-8410
出版年度：2013
卷号：5
期号：1
页码：19-28
DOI：10.4236/jilsa.2013.51003
出版社：Scientific Research Publishing
摘要：In this paper we study the problem of model selection for a linear programming-based support vector machine for regression. We propose generalized method that is based on a quasi-Newton method that uses a globalization strategy and an inexact computation of first order information. We explore the case of two-class, multi-class, and regression problems. Simulation results among standard datasets suggest that the algorithm achieves insignificant variability when measuring residual statistical properties.
关键词：Hyper-Parameter Estimation; Support Vector Regression; Machine Learning; Data Mining
