摘要
Optimization algorithm solving Lagrangian multipliers is the key of training SVM,determining the perfor-mance of SVM ,affecting practical applications of SVM in various fields widely. Some kinds of optimization algorithmsin SVM of overseas are introduced. We classify the optimization algorithms into two kinds: 1. the algorithms based onOsuna's decomposition strategy; 2. The iterative algorithms based on the changes of SVM formulation proposed byO. L. Mangasarian. We also analyze the characteristics of various optimization algorithms in SVM ,and predicting thetrend of research on optimization algorithm in SVM.
Optimization algorithm solving Lagrangian multipliers is the key of training SVM, determining the performance of SVM, affecting practical applications of SVM in various fields widely. Some kinds of optimization algorithms in SVM of overseas are introduced. We classify the optimization algorithms into two kinds : 1. the algorithms based on Osuna's decomposition strategy; 2. The iterative algorithms based on the changes of SVM formulation proposed by O. L. Mangasanan. We also analyze the characteristics of various optimization algorithms in SVM,and predicting the trend of research on optimization algorithm in SVM.
出处
《计算机科学》
CSCD
北大核心
2003年第3期12-15,20,共5页
Computer Science
基金
国家自然科学基金(编号:20076041)
