| 支持向量机子问题的算法研究 |
| |
| 引用本文： | 付三平,于静,韩丛英. 支持向量机子问题的算法研究[J]. 山东理工大学学报：自然科学版, 2012, 0(1): 23-25 |
| |
| 作者姓名： | 付三平 于静 韩丛英 |
| |
| 作者单位： | 山东科技大学信息科学与工程学院 |
| |
| 基金项目： | 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.
|
| 关 键 词： | 二次规划 支持向量机 界约束 有限记忆BFGS |
The algorithm research of subproblems of the support vector machines |
| |
| FU San-ping,YU Jing,HAN Cong-ying. The algorithm research of subproblems of the support vector machines[J]. Journal of Shandong University of Technology:Science and Technology, 2012, 0(1): 23-25 |
| |
| Authors: | FU San-ping YU Jing HAN Cong-ying |
| |
| Affiliation: | (College of Information Science and Engineering,Shandong University of Science and Technology,Qingdao 266590,China) |
| |
| Abstract: | 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. |
| |
| Keywords: | quadratic programming support vector machines bound constraint limited memory BFGS |
| 本文献已被 CNKI 等数据库收录！ |
|
