Abstract
The support vector machine (SVM) is considered to be one of the effective machine learning with high generalization performance. We can formulate SVM as the convex quadratic programming problem and calculate the optimal solutions. On the other hand, the method with penalty vectors is proposed as of the methods to handle uncertain data. This method is used in clustering methods and can naturally formulate uncertainty to optimization problem. In this paper, we propose a new algorithm that is a support vector machine quoted penalty vector method.
