支持向量机子问题的算法研究  

The algorithm research of subproblems of the support vector machines

作　　者：付三平[1] 于静[1] 韩丛英[1] 

机构地区：[1]山东科技大学信息科学与工程学院,山东青岛266590

出　　处：《山东理工大学学报（自然科学版）》2012年第1期23-25,共3页Journal of Shandong University of Technology:Natural Science Edition

基　　金：国家自然科学基金资助项目(10971122;11101420);山东省自然科学基金资助项目(Y2008A01)

摘　　要：求解支持向量机大规模分类问题时,系数矩阵的存储和计算是非常困难的.借助分解技术,把问题分解成多个维数较低的二次规划问题.利用增广拉格朗日函数将子问题转化成只含有界约束的形式,再用修正子空间有限记忆BFGS方法解子问题,节省了存储空间,提高了求解效率.The storage and computing of coefficient matrix were very difficult for solving large-scale SVMs.At each decomposition iteration,the problem was split up into smaller quadratic programming subproblems.The augmented lagrangian scheme was used to transform the subproblems into problems only with a set of bound constrains,then the subproblems were solved by modified subspace limited memory BFGS algorithm.This method could save storage space considerably and improve the efficiency.

关 键 词：二次规划 支持向量机 界约束 有限记忆BFGS 

分 类 号：O224[理学—运筹学与控制论]