Class-size Independent Generalization Analsysis of Some Discriminative Multi-Category Classification

@inproceedings{Zhang2004ClasssizeIG,
  title={Class-size Independent Generalization Analsysis of Some Discriminative Multi-Category Classification},
  author={Tong Zhang},
  booktitle={NIPS},
  year={2004}
}
We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtain an expected generalization bound for a standard formulation of multi-category support vector machines. Based on the theoretical result, we argue that the formulation over-penalizes misclassification error, which in theory may lead to poor generalization performance. A remedy, based on a generalization of multi… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

Parameter estimation for statistical parsing models: Theory and practice of distribution-free methods

  • Michael Collins
  • IWPT,
  • 2001
Highly Influential
3 Excerpts

Statistical analysis of some multi-category large margin classification methods.Journal of Machine Learning Research

  • Tong Zhang
  • 2004
1 Excerpt

Statistical analysis of some multi - category large margin classification methods

  • Tong Zhang
  • Neural Computation
  • 2003

Similar Papers

Loading similar papers…