Training Support Vector Machines via SMO-Type Decomposition Methods
(invited lecture for ALT 2005)

Authors: Pai-Hsuen Chen, Rong-En Fan, and Chih-Jen Lin

Affiliation: Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan

Source: Algorithmic Learning Theory, 16th International Conference, ALT 2005, Singapore, October 2005, Proceedings, (Sanjay Jain, Hans Ulrich Simon and Etsuji Tomita, Eds.), Lecture Notes in Artificial Intelligence 3734, pp. 45 - 62, Springer 2005.

Abstract. This article gives a comprehensive study on SMO-type (Sequential Minimal Optimization) decomposition methods for training support vector machines. We propose a general and flexible selection of the two-element working set. Main theoretical results include 1) a simple asymptotic convergence proof, 2) a useful explanation of the shrinking and caching techniques, and 3) the linear convergence of this method. This analysis applies to any SMO-type implementation whose selection falls into the proposed framework.

©Copyright 2005 Springer