Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

On the Robustness of Regularized Pairwise Learning Methods Based on Kernels

Title data

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

Related URLs

Project information

Project financing: Deutsche Forschungsgemeinschaft

Abstract in another language

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.

Further data

Item Type: Article in a journal
Refereed: Yes
Keywords: machine learning; pairwise loss function; regularized risk; robustness
Institutions of the University: Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics > Chair Mathematics VII - Stochastics > Chair Mathematics VII - Stochastics - Univ.-Prof. Dr. Andreas Christmann
Faculties
Faculties > Faculty of Mathematics, Physics und Computer Science
Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics
Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics > Chair Mathematics VII - Stochastics
Result of work at the UBT: Yes
DDC Subjects: 500 Science > 510 Mathematics
Date Deposited: 14 Oct 2015 09:03
Last Modified: 28 Sep 2016 05:37
URI: https://eref.uni-bayreuth.de/id/eprint/20475