The new interpretation of support vector machines on statistical learning theory

作     者：ZHANG ChunHua 1 , TIAN YingJie 2 & DENG NaiYang 3,1 School of Information, Renmin University of China, Beijing 100872, China 2 Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing 100080, China 3 College of Science, China Agricultural University, Beijing 100083, China 

作者机构：School of Information Renmin University of China Beijing China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing China College of Science China Agricultural University Beijing China 

出 版 物：《Science China Mathematics》 (中国科学：数学（英文版）)

年 卷 期：2010年第53卷第1期

页      面：151-164页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Natural Science Foundation of China(Grant No. 10971223,10601064) Key Project of National Natural Science Foundation of China (Grant No.10631070,70531040) the Science Foundation of Renmin University of China (Grant No.06XNB055) 

主　　题：C-support vector classification the minimization principle of the structural risk KKT conditions 

摘      要：This paper is concerned with the theoretical foundation of support vector machines (SVMs). The purpose is to develop further an exact relationship between SVMs and the statistical learning theory (SLT). As a representative, the standard C-support vector classification (C-SVC) is considered here. More precisely, we show that the decision function obtained by C-SVC is just one of the decision functions obtained by solving the optimization problem derived directly from the structural risk minimization principle. In addition, an interesting meaning of the parameter C in C-SVC is given by showing that C corresponds to the size of the decision function candidate set in the structural risk minimization principle.