Multi-Objective Models for Sparse Optimization in Linear Support Vector Machine Classification

The design of linear Support Vector Machine (SVM) classification techniques is generally a Multi-objective Optimization Problem (MOP). These require finding appropriate trade-offs between two objectives, such as the amount misclassified training data (classification error) and number non-zero elements separator hyperplane. In this article, we review several SVM models in form multi-objective optimization. We put particular emphasis on applying sparse optimization (in terms minimization hyperplane) to Feature Selection (FS) for SVM. Our primary purpose demonstrate advantages considering MOPs. cases, can obtain set Pareto optimal solutions instead one solution single-objective cases. results these SVMs are reported some datasets. test problems specifically designed challenge components normal vector used datasets models.