Angle-based Multicategory Distance-weighted SVM

Abstract

Classification is an important supervised learning technique with numerous applications. We develop an angle-based multicategory distance-weighted support vector machine (MDWSVM) classification method that is motivated from the binary distance-weighted support vector machine (DWSVM) classification method. The new method has the merits of both support vector machine (SVM) and distance-weighted discrimination (DWD) but also alleviates both the data piling issue of SVM and the imbalanced data issue of DWD. Theoretical and numerical studies demonstrate the advantages of MDWSVM method over existing angle-based methods.