Learning Rates of Kernel-Based Robust Classification

This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers. A comparison relationship between the excess misclassification error and the excess generalization error is provided; from this, along with the convex analysis theory, a kind of learning rate is derived. The results show that the performance of the classifier is effected by the outliers, and the extent of impact can be controlled by choosing the homotopy parameters properly.