Rie Kubota Ando, Tong Zhang
ACL 2005
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-category logistic regression (conditional maximum entropy), is then proposed, and its theoretical properties are examined.
Rie Kubota Ando, Tong Zhang
ACL 2005
Tong Zhang
JMLR
Tong Zhang
Neural Computation
Rie Johnson, Tong Zhang
JMLR