Decomposition methods for linear support vector machines

@article{Chung2003DecompositionMF,
  title={Decomposition methods for linear support vector machines},
  author={Kai-Min Chung and Wei-Chun Kao and Tony Sun and Chih-Jen Lin},
  journal={2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).},
  year={2003},
  volume={4},
  pages={IV-868}
}
  • Kai-Min Chung, Wei-Chun Kao, +1 author Chih-Jen Lin
  • Published 2003
  • Computer Science
  • 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • We explain that decomposition methods, in particular, SMO-type algorithms, are not suitable for linear SVMs with more data than attributes. To remedy this difficulty, we consider a recent result by S.S. Keerthi and C.-J. Lin (see http://www.csie.ntu.edu.tw//spl sim/cjlin/papers/limit.ps.gz, 2002) that for an SVM which is not linearly separable, after C is large enough, the dual solutions are at similar faces. Motivated by this property, we show that alpha seeding is extremely useful for solving… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 11 CITATIONS

    Decomposition Methods for Linear Support Vector Machines

    VIEW 2 EXCERPTS
    CITES METHODS

    Improving Efficiency of SVM k-Fold Cross-Validation by Alpha Seeding

    • Zeyi Wen, Bin Li, +3 authors Rui Zhang
    • Computer Science, Mathematics
    • AAAI
    • 2017
    VIEW 3 EXCERPTS
    CITES METHODS

    Fairness testing: testing software for discrimination

    VIEW 1 EXCERPT
    CITES METHODS

    Evolutionary Optimization of Kernel Weights Improves Protein Complex Comembership Prediction

    References

    Publications referenced by this paper.
    SHOWING 1-7 OF 7 REFERENCES

    A fast iterative nearest point algorithm for support vector machine classifier design

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    Making Large-Scale SVM Learning Practical

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Asymptotic behaviors of suppon vector machines with

    • S. S . Keenhi, C. J . Lin
    • Gaussian kernel,
    • 2002

    Decompasition methods for linear suppon vector machines

    • KM. Chung, W.-C. Kao. T. Sun, C.-I. Lin
    • Technical repon. Depanment of Computer Science and Information Engineering, National Taiwan Uniuersity,
    • 2002

    LIBSVM: a l ibmn, for support vector machines

    • C.-C. Chang, CJ. Lin
    • 2001
    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Lagrangian suppon vector machines

    • L. Mangararian, D. K. Musicant
    • JournalofMachim Learning Rerearch,
    • 2001

    RSVM Reduced suppon veclor machines

    • Y.-I. Lee, 0. L. Mangararian
    • In Proceedings of the First SIAM lnrernotionul Conference on Data Mining,
    • 2001