Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms

  • Authors:
  • S. S. Keerthi

  • Affiliations:
  • Dept. of Mech. Eng., Nat. Univ. of Singapore

  • Venue:
  • IEEE Transactions on Neural Networks
  • Year:
  • 2002

Quantified Score

Hi-index 0.01

Visualization

Abstract

The paper discusses implementation issues related to the tuning of the hyperparameters of a support vector machine (SVM) with L2 soft margin, for which the radius/margin bound is taken as the index to be minimized, and iterative techniques are employed for computing radius and margin. The implementation is shown to be feasible and efficient, even for large problems having more than 10000 support vectors.