On the Consistency of Multiclass Classification Methods

  • Ambuj Tewari
  • Peter L. Bartlett
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3559)

Abstract

Binary classification methods can be generalized in many ways to handle multiple classes. It turns out that not all generalizations preserve the nice property of Bayes consistency. We provide a necessary and sufficient condition for consistency which applies to a large class of multiclass classification methods. The approach is illustrated by applying it to some multiclass methods proposed in the literature.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bartlett, P.L., Jordan, M.I., McAuliffe, J.D.: Large margin classifiers: Convex Loss, Low Noise and Convergence rates. Advances in Neural Information Processing Systems 16 (2004)Google Scholar
  2. 2.
    Bredensteiner, E.J., Bennett, K.P.: Multicategory Classification by Support Vector Machines. Computational Optimization and Applications 12, 35–46 (1999)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Crammer, K., Singer, Y.: On the Algorithmic Implementation of Kernel-based Vector Machines. Journal of Machine Learning Research 2, 265–292 (2001)CrossRefGoogle Scholar
  4. 4.
    Jiang, W.: Process Consistency for AdaBoost. Annals of Statistics 32(1), 13–29 (2004)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Lee, Y., Li, Y., Wahba, G.: Multicategory Support Vector Machines: Theory and Application to the Classification of Microarray Data and Satellite Radiance Data. Journal of the American Statistical Association 99(465), 67–81 (2004)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Lugosi, G., Vayatis, N.: On the Bayes-risk Consistency of Regularized Boosting Methods. Annals of Statistics 32(1), 30–55 (2004)MATHMathSciNetGoogle Scholar
  7. 7.
    Pollard, D.: Convergence of Stochastic Processes. Springer, New York (1984)MATHGoogle Scholar
  8. 8.
    Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)MATHGoogle Scholar
  9. 9.
    Steinwart, I.: Consistency of Support Vector Machines and Other Regularized Kernel Classifiers. IEEE Transactions on Information Theory 51(1), 128–142 (2005)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Weston, J., Watkins, C.: Multi-class support vector machines. Technical Report CSD-TR-98-04, Department of Computer Science, Royal Holloway College, University of London (1998)Google Scholar
  11. 11.
    Zhang, T.: An Infinity-sample Theory For Multi-category Large Margin Classification. Advances in Neural Information Processing Systems 16 (2004)Google Scholar
  12. 12.
    Zhang, T.: Statistical Analysis of Some Multi-Category Large Margin Classification Methods. Journal of Machine Learning Research 5, 1225–1251 (2004)Google Scholar
  13. 13.
    Zhang, T.: Statistical Behavior and Consistency of Classification Methods Based on Convex Risk Minimization. Annals of Statistics 32(1), 56–85 (2004)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ambuj Tewari
    • 1
  • Peter L. Bartlett
    • 2
  1. 1.Division of Computer ScienceUniversity of CaliforniaBerkeley
  2. 2.Division of Computer Science and Department of StatisticsUniversity of CaliforniaBerkeley

Personalised recommendations