Machine Learning

, Volume 54, Issue 3, pp 195–209

A Meta-Learning Method to Select the Kernel Width in Support Vector Regression

  • Carlos Soares
  • Pavel B. Brazdil
  • Petr Kuba
Article

DOI: 10.1023/B:MACH.0000015879.28004.9b

Cite this article as:
Soares, C., Brazdil, P.B. & Kuba, P. Machine Learning (2004) 54: 195. doi:10.1023/B:MACH.0000015879.28004.9b

Abstract

The Support Vector Machine algorithm is sensitive to the choice of parameter settings. If these are not set correctly, the algorithm may have a substandard performance. Suggesting a good setting is thus an important problem. We propose a meta-learning methodology for this purpose and exploit information about the past performance of different settings. The methodology is applied to set the width of the Gaussian kernel. We carry out an extensive empirical evaluation, including comparisons with other methods (fixed default ranking; selection based on cross-validation and a heuristic method commonly used to set the width of the SVM kernel). We show that our methodology can select settings with low error while providing significant savings in time. Further work should be carried out to see how the methodology could be adapted to different parameter setting tasks.

meta-learning parameter setting support vector machines Gaussian kernel learning rankings 
Download to read the full article text

Supplementary material

APp.5264924_1.pdf
Supplementary material

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Carlos Soares
    • 1
  • Pavel B. Brazdil
    • 1
  • Petr Kuba
    • 2
  1. 1.LIACC/Faculty of EconomicsUniversity of PortoPortugal
  2. 2.Masaryk UniversityCzech Republic

Personalised recommendations