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

Authors:
Lingfeng Niu;Ya-Xiang Yuan
Affiliations:
Research Center on Fictitious Economy and Data Science, Graduate University of Chinese Academy Sciences, AMSS, CAS, Beijing, People's Republic of China,State Key Laboratory of Scientific and Engin ...;State Key Laboratory of Scientific and Engineering Computing, Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, CAS, Beijing, People's Republic of China
Venue:
Optimization Methods & Software
Year:
2011

Citing 0
Cited 1

Neural networks letter: Training the max-margin sequence model with the relaxed slack variables

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.