On the Robustness of Regularized Pairwise Learning Methods Based on Kernels

Titelangaben

Christmann, Andreas ; Zhou, Ding-Xuan:
On the Robustness of Regularized Pairwise Learning Methods Based on Kernels.
In: Journal of Complexity. Bd. 37 (2016) . - S. 1-33.
ISSN 0885-064X
DOI: https://doi.org/10.1016/j.jco.2016.07.001

Weitere URLs

Angaben zu Projekten

Abstract

Regularized empirical risk minimization including support vector machines plays an important role in machine learning theory. In this paper regularized pairwise learning (RPL) methods based on kernels will be investigated. One example is regularized minimization of the error entropy loss which has recently attracted quite some interest from the viewpoint of consistency and learning rates. This paper shows that such RPL methods have additionally good statistical robustness properties, if the loss function and the kernel are chosen appropriately. We treat two cases of particular interest: (i) a bounded and non-convex loss function and (ii) an unbounded convex loss function satisfying a certain Lipschitz type condition.