A simple decomposition method for support vector machines

被引：224
|
作者：
Hsu, CW [1 ]
Lin, CJ [1 ]
机构：
[1] Natl Taiwan Univ, Dept Comp Sci & Informat Engn, Taipei 106, Taiwan
来源：
MACHINE LEARNING | 2002年 / 46卷 / 1-3期
关键词：
support vector machines; decomposition methods; classification;
D O I：
10.1023/A:1012427100071
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The decomposition method is currently one of the major methods for solving support vector machines. An important issue of this method is the selection of working sets. In this paper through the design of decomposition methods for bound-constrained SVM formulations we demonstrate that the working set selection is not a trivial task. Then from the experimental analysis we propose a simple selection of the working set which leads to faster convergences for difficult cases. Numerical experiments on different types of problems are conducted to demonstrate the viability of the proposed method.
引用
收藏
页码：291 / 314
页数：24
相关论文
共 50 条
  • [31] Global convergence analysis of decomposition methods for support vector machines
    Takahashi, N
    Nishi, T
    2004 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL 5, PROCEEDINGS, 2004, : 728 - 731
  • [32] Global convergence of decomposition learning methods for support vector machines
    Takahashi, Norikazu
    Nishi, Tetsuo
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06): : 1362 - 1369
  • [33] Structured multicategory support vector machines with analysis of variance decomposition
    Lee, Yoonkyung
    Kim, Yuwon
    Lee, Sangjun
    Koo, Ja-Yong
    BIOMETRIKA, 2006, 93 (03) : 555 - 571
  • [34] Empirical mode decomposition based on support vector regression machines
    College of Computer Science and Technology, Harbin Engineering University, Harbin 15001, China
    Harbin Gongcheng Daxue Xuebao, 2007, 7 (779-784): : 779 - 784
  • [35] Polynomial-Time Decomposition Algorithms for Support Vector Machines
    Don Hush
    Clint Scovel
    Machine Learning, 2003, 51 : 51 - 71
  • [36] Feasible Direction Decomposition Algorithms for Training Support Vector Machines
    Pavel Laskov
    Machine Learning, 2002, 46 : 315 - 349
  • [37] Decomposition techniques for training linear programming support vector machines
    Torii, Yusuke
    Abe, Shigeo
    NEUROCOMPUTING, 2009, 72 (4-6) : 973 - 984
  • [38] Multiresolution signal decomposition and approximation based on support vector machines
    Shang, Zhaowei
    Tang, Yuan Yan
    Fang, Bin
    Wen, Jing
    Ong, Yat Zhou
    INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2008, 6 (04) : 593 - 607
  • [39] Polynomial-time decomposition algorithms for support vector machines
    Hush, D
    Scovel, C
    MACHINE LEARNING, 2003, 51 (01) : 51 - 71
  • [40] Traffic Sign Array Decomposition Using Support Vector Machines
    Gil-Jimenez, P.
    Gomez-Moreno, H.
    Siegmann, P.
    Lafuente-Arroyo, S.
    Maldonado-Bascon, S.
    2008 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, 2008, : 644 - 649
12345