The Bayesian Committee Support Vector Machine

A. Schwaighofer and V. Tresp

Abstract:

Empirical evidence indicates that the training time for the support vector machine (SVM) scales to the square of the number of training data points. In this paper, we introduce the Bayesian committee support vector machine (BC-SVM) and achieve an algorithm for training the SVM which scales linearly in the number of training data points. We verify the good performance of the BC-SVM using several data sets.

Reference: A. Schwaighofer and V. Tresp. The Bayesian committee support vector machine. In G. Dorffner, H. Bischof, and K. Hornik, editors, Artificial Neural Networks - ICANN 2001, Lecture Notes in Computer Science2130, pages 411-417. Springer Verlag, 2001.