Fast Training Support Vector Machines Using Parallel Sequential Minimal Optimization

摘要：

One of the key factors that limit Support VectorMachines(SVMs)application in large sampleproblems is that the large-scale quadraticprogramming(QP)that arises from SVMs trainingcannot be easily solved via standard QPtechnique.The Sequential Minimal Optimization(SMO)is current one of the major methods for solvingSVMs.This method,to a certain extent,can decreasethe degree of difficulty of a QP problem throughdecomposition strategies,however,the high trainingprice for saving memory space must be endured.Inthis paper,an algorithm in the light of the idea ofparallel computing based on SymmetricMultiprocessor(SMP)machine is improved.The newtechnique has great advantage in terms of speedinesswhen applied to problems with large training sets andhigh dimensional spaces without reducinggeneralization performance of SVMs.

作者: Zhi-Qiang Zeng Hong-Bin Yu Hua-Rong Xu Yan-Qi Xie Ji Gao

作者单位: Department of Computer Science and Technology,Xiamen University of Technology,Xiamen 361024,China Department of Computer Science and Technology,Zhengzhou University of Light Industry,Zhengzhou 45000 Department of Physics and Electromechanical,Xiamen University,Xiamen 361005,China Department of Computer Science and Engineering,Zhejiang University,Hangzhou 310027,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 997-1001

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）