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

被引:1
作者
Pirouz, Behzad [1 ]
Pirouz, Behrouz [2 ]
机构
[1] Univ Calabria, Dept Comp Engn Modelling Elect & Syst Engn, I-87036 Arcavacata Di Rende, Italy
[2] Univ Calabria, Dept Civil Engn, I-87036 Arcavacata Di Rende, Italy
关键词
support vector machine; feature selection; sparse optimization; multi-objective optimization problems; multi-objective machine learning; EPSILON-CONSTRAINT METHOD;
D O I
10.3390/math11173721
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The design of linear Support Vector Machine (SVM) classification techniques is generally a Multi-objective Optimization Problem (MOP). These classification techniques require finding appropriate trade-offs between two objectives, such as the amount of misclassified training data (classification error) and the number of non-zero elements of the separator hyperplane. In this article, we review several linear SVM classification models in the form of multi-objective optimization. We put particular emphasis on applying sparse optimization (in terms of minimization of the number of non-zero elements of the separator hyperplane) to Feature Selection (FS) for multi-objective optimization linear SVM. Our primary purpose is to demonstrate the advantages of considering linear SVM classification techniques as MOPs. In multi-objective cases, we can obtain a set of Pareto optimal solutions instead of one optimal solution in single-objective cases. The results of these linear SVMs are reported on some classification datasets. The test problems are specifically designed to challenge the number of non-zero components of the normal vector of the separator hyperplane. We used these datasets for multi-objective and single-objective models.
引用
收藏
页数:18
相关论文
共 66 条
[1]  
[Anonymous], 1909, MANUEL D'ECONOMIE POLITIQUE
[2]  
Bennett KP, 1998, IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, P2396, DOI 10.1109/IJCNN.1998.687237
[3]  
Bi J., 2003, P 20 INT C MACHINE L, P35
[4]  
Bishop C.M., 1996, NEURAL NETWORKS PATT
[5]  
Bradley P.S., 1998, PROCEEDING 15 INT C, P82
[6]  
CHANKONG V, 1983, LARGE SCALE SYST, V5, P1
[7]  
Chankong V., 1983, MULTIOBJECTIVE DECIS
[8]  
Coello C.A., 2002, EVOLUTIONARY ALGORIT, DOI [10.1007/978-1-4757-5184-0, DOI 10.1007/978-1-4757-5184-0]
[9]  
Coleman T.F., 1984, Large Sparse Numerical Optimization, DOI [10.1007/3-540-12914-6, DOI 10.1007/3-540-12914-6]
[10]  
Collette Y., 2003, MULTIOBJECTIVE OPTIM