期刊文献+

面向原问题求解的拟牛顿SVM回归算法研究 被引量:1

Quasi-Newton SVM Regression Algorithm for Solving Primal Problem
下载PDF
导出
摘要 研究了支持向量机(SVM)的原问题优化及其回归算法.在分析原问题与对偶问题最优化关系的基础上,引入了一种原问题求解的L-MBFGS-SVR算法.该算法在求解无约束优化问题时,引入了一类新的BFGS拟牛顿算法.它利用迭代的梯度和函数值来近似逆Hessian矩阵,以降低计算复杂性;并结合有限内存技术,来解决数据存储问题.仿真表明,该算法总体上优于IHLF-SVR-RFN和SMO算法,是一种有效的大样本非线性回归建模方法. The primal problem optimization of SVM (Support Vector Machine) and its regression algorithm are studied. After analyzing the relationship between primal and dual optimization, an L - MBFGS - SVR algorithm based on solving primal problem is introduced. For solving the unconstrained optimization problem, the algorithm introduces a new BFGS Quasi - Newton optimization method. It approximates the converse of Hessian matrix by the iterative gradient and function value to reduce the computation complexity, and makes use of the limited memory technique to solve the data memory problem. The experiments show that the L - MBFGS - SVR is better than IHLF- SVR -RFN or SMO in general, and it is an effective nonlinearity regression modeling method for large samples.
出处 《昆明理工大学学报(自然科学版)》 CAS 北大核心 2011年第5期43-49,共7页 Journal of Kunming University of Science and Technology(Natural Science)
关键词 支持向量机 对偶问题 拟牛顿 有限内存 SVM dual problem quasi - Newton limited memory
  • 相关文献

参考文献12

  • 1陈宝林最优化理论与算法[M].
  • 2Keerthi S S,,DeCoste D M.A modified finite Newton method for fast solution of large scale linear SVMS. Journal of Ma-chine Learning Research . 2005
  • 3Liefeng Bo,Ling Wang,Licheng Jiao.Recursive finite Newton algorithm for support vector regression in the primal. Neural Computing and Applications . 2007
  • 4Chengxian Xu,Jianzhong Zhong.A survey of quasi-Newton equations and quasi-Newton methods for optimization. Annals of Operations Research . 2001
  • 5Yueting Yang,Chengxian Xu.A compact limited-memory method for large scale unconstrained optimization. The Euro-pean Journal of Operational Research . 2007
  • 6Wahba G,Lin Yi,et al.Generalized approximate cross validation for support vector machines or another way to look at mar-gin quantities. Advances in Large Margin Classifiers . 2000
  • 7Fung G,Mangasarian O L.Finite Newton Method for Lagrangian Sup-port Vector Machine Classification. Neurocomputing . 2003
  • 8Dennis J E Jr and More,J J.Qaasi-Newton Methods,Motivation and Theory. SIAM Review . 1977
  • 9D Liu,J Nocedal.On the limited memory BFGS method for large scale optimization. Mathematical Programming . 1989
  • 10Huber,P. Robust Statistics . 1981

同被引文献14

  • 1汪晓东,张长江,张浩然,冯根良,许秀玲.传感器动态建模的最小二乘支持向量机方法[J].仪器仪表学报,2006,27(7):730-733. 被引量:18
  • 2白鹏,张喜斌,陈长兴,朱长纯.基于支持向量机的压力传感器校正模型[J].空军工程大学学报(自然科学版),2007,8(5):37-40. 被引量:10
  • 3杨红军,运高谦.电涡流传感器温度特性的研究[J].吉林省教育学院报,2010(9):153.154.
  • 4Abbasi, Abduli, MA,Omidvar, Baghvand.Forecasting Mu- nicipal Solid waste Generation by Hybrid Support Vector Machine and Partial Least Square Model [J]. INTERNA- TIONAL JOURNAL OF ENVIRONMENTAL RE- SEARCH,2012,7(1):27-38.
  • 5Dong Seong Kim,ha-nam nguyen,jong sou park, Genetic Al- gorithm to Improve SVM Based Network Intrusion Detec- tion System[J].lEEE Computer Socitey ,2005,155 - 158.
  • 6Jinfeng Shi, Xiangyang Xu, Yaping Dai. Predictive Func- tional Control Algorithm Design Based on SVM Model of Batch Reactor [J]. International Conference on Mechanicaland Electrical Technology,2011,3:132-136.
  • 7Anton, Nieto, Viejo, Vilan, JAV.Support Vector Machines Used to Estimate the Battery State of Charge [J]. IEEE TRANSACTIONS ON POWER ELECTRONICS,2012,28 (12):5919-5926.
  • 8State, L.a, Cocianu, C.b, Mircea, M.b Tuning the SVM para- meters to class variability[J]. Advanced Science Letters Vol- ume,2013,19(12):3660-3664.
  • 9蒋寿生,鄂加强,刘云卿,龚金科.基于最小二乘支持向量机的车用铂电阻温度传感器非线性校正[J].湖南农业大学学报(自然科学版),2008,34(5):613-616. 被引量:3
  • 10程山英.传感器动态建模算法的仿真研究[J].计算机仿真,2012,29(10):140-142. 被引量:2

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部