A parallel decomposition algorithm for training multiclass kernel-based vector machines

We present a decomposition method for training Crammer and Singer's multiclass kernel-based vector machine model. A new working set selection rule is proposed. Global convergence of the algorithm based on this selection rule is established. Projected gradient method is chosen to solve the resul...

Full description

Saved in:
Bibliographic Details
Published inOptimization methods & software Vol. 26; no. 3; pp. 431 - 454
Main Authors Niu, Lingfeng, Yuan, Ya-Xiang
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 01.06.2011
Taylor & Francis Ltd
Subjects
Algorithms
decomposition method
Kernel-based vector machines
parallel algorithm
projected gradient
Studies
Online AccessGet full text

Cover

More Information
Summary:We present a decomposition method for training Crammer and Singer's multiclass kernel-based vector machine model. A new working set selection rule is proposed. Global convergence of the algorithm based on this selection rule is established. Projected gradient method is chosen to solve the resulting quadratic subproblem at each iteration. An efficient projection algorithm is designed by exploiting the structure of the constraints. Parallel strategies are given to utilize the storage and computational resources available on the multiprocessor system. Numerical experiment on benchmark problems demonstrates that the good classification accuracy and remarkable time saving can be achieved.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1055-6788
1029-4937
DOI:10.1080/10556788.2011.556633