支持向量顺序回归机的统计学习基础  

Statistical Learning Element of Support Vector Ordinal Regression Machine

作　　者：阳红英[1] 杨志霞[1] 

机构地区：[1]新疆大学数学与系统科学学院,乌鲁木齐830046

出　　处：《运筹学学报》2011年第3期70-80,共11页Operations Research Transactions

基　　金：国家自然科学基金(10801112;11161045)

摘　　要：对处理顺序回归问题的支持向量顺序回归机的统计学习理论基础进行研究.首先,利用结构风险最小化原则推导出一种顺序回归机,称之为结构风险最小化顺序回归机,其次,证明了结构风险最小化顺序回归机与支持向量顺序回归机解之间的关系.进一步从统计学习的角度证明了支持向量顺序回归机是结构风险最小化原则的一种直接实现,并给出了惩罚参数C的含义.For support vector ordinal regression machine, its statistical learning element is studied in this paper. Using structural risk minimization principle, we reduce one of ordinal regression machine, which is called structural risk minimization ordinal regression machine. Furthermore, the relation of solution between structural risk minimization ordinal regression machine and support vector ordinal regression machine is proved. From the statistical point of view, support vector ordinal regression machine is a direct implementation of structural risk minimization principle.

关 键 词：最优化问题 顺序回归问题 支持向量顺序回归机 结构风险最小化顺序回归机 

分 类 号：O224[理学—运筹学与控制论]