A continuation method for semi-supervised SVMs

Semi-Supervised Support Vector Machines (S3 VMs) are an appealing method for using unlabeled data in classification: their objective function favors decision boundaries which do not cut clusters. However their main problem is that the optimization problem is non-convex and has many local minima, which often results in suboptimal performances. In this paper we propose to use a global optimization technique known as continuation to alleviate this problem. Compared to other algorithms minimizing the same objective function, our continuation method often leads to lower test errors.

• Type: Conference
• Year: 2006
• Where: ICML
• Authors: Olivier Chapelle, Mingmin Chi, Alexander Zien
• Keywords: Continuation Method, ICML 2006, Machine Learning, Objective Function Favors, Optimization Problem