Literature by the same author
plus at Google Scholar

Bibliografische Daten exportieren
 

On the Robustness of Kernel-Based Pairwise Learning

Title data

Gensler, Patrick ; Christmann, Andreas:
On the Robustness of Kernel-Based Pairwise Learning.
In: Steland, Ansgar ; Tsui, Kwok-Leung (ed.): Artificial Intelligence, Big Data and Data Science in Statistics : Challenges and Solutions in Environmetrics, the Natural Sciences and Technology. - Cham : Springer , 2022 . - pp. 111-153
ISBN 978-3-031-07154-6
DOI: https://doi.org/10.1007/978-3-031-07155-3_5

Official URL: Volltext

Project information

Project financing: Deutsche Forschungsgemeinschaft
DFG Grant CH 291/3-1

Abstract in another language

It is shown that many results on the statistical robustness of kernel-based pairwise learning can be derived under basically no assumptions on the input and output spaces. In particular, neither moment conditions on the conditional distribution of Y  given X = x nor the boundedness of the output space is needed. We obtain results on the existence and boundedness of the influence function and show qualitative robustness of the kernel-based estimator. The present paper generalizes results by Christmann and Zhou by allowing the prediction function to take two arguments and can thus be applied in a variety of situations such as ranking, similarity learning and distance metric learning.

Further data

Item Type: Article in a book
Refereed: Yes
Keywords: Kernel methods; Machine Learning; Support Vector Machines; Robust Statistics
Institutions of the University: Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics > Chair Mathematics VII - Stochastics
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
Result of work at the UBT: Yes
DDC Subjects: 000 Computer Science, information, general works > 004 Computer science
500 Science > 510 Mathematics
Date Deposited: 20 Dec 2022 08:54
Last Modified: 20 Dec 2022 08:54
URI: https://eref.uni-bayreuth.de/id/eprint/73081