An Overview on Second Order Cone Programming Formulations for Support Vector Machine Algorithms

In this tutorial we give an overview of the basic ideas second order cone programming (SOCP) formulations machines for support vector machine (SVM) algorithms. Furthermore, we include a summary of currently used algorithms for training SVM algorithms, covering both the quadratic (or convex) programming part and advanced methods for dealing with imbalanced and multiclass datasets. Finally, we mention some modifications and extensions that have been applied to the standard SOCP algorithm, and discuss the aspect of regularization from a SOCP-SVM perspective.