On the Consistency of Multiclass Classification Methods
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.
Unable to display preview. Download preview PDF.
- 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
- 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.Zhang, T.: An Infinity-sample Theory For Multi-category Large Margin Classification. Advances in Neural Information Processing Systems 16 (2004)Google Scholar
- 12.Zhang, T.: Statistical Analysis of Some Multi-Category Large Margin Classification Methods. Journal of Machine Learning Research 5, 1225–1251 (2004)Google Scholar