Copositive Optimization Relaxation for Semi-supervised Support Vector Machines

摘要

Given a training set of labeled data and a working set of unlabeled data, semi-supervised support vector machines (S3VMs) are based on applying the margin maximization principle to both labeled and unlabeled data. S3VMs are formulated as a mixed integer programming (MIP) problem.In this paper, we present a copositive optimization (CO) relaxation for the MIP problem associated with S3VMs.