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

S S Keerthi

doi:10.1109/TNN.2002.1031955

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

IEEE Trans Neural Netw. 2002;13(5):1225-9. doi: 10.1109/TNN.2002.1031955.

Author

S S Keerthi¹

Affiliation

¹ Dept. of Mech. Eng., Nat. Univ. of Singapore, Singapore.

PMID: 18244520
DOI: 10.1109/TNN.2002.1031955

Abstract

The paper discusses implementation issues related to the tuning of the hyperparameters of a support vector machine (SVM) with L/sub 2/ 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.