at Google ScholarTitle data
Gensler, Patrick ; Christmann, Andreas:
On the robustness of kernel-based pairwise learning.
Bayreuth
,
2020
. - 34 S.
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 (2016) by allowing the prediction function to take two arguments and can thus be applied in a variety of situations such as ranking.
Further data
| Item Type: | Preprint, postprint |
|---|---|
| Keywords: | robustness; influence function; consistency; machine learning; pairwise loss function; regularized risk |
| 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: | 04 Nov 2020 10:28 |
| Last Modified: | 04 Nov 2020 10:28 |
| URI: | https://eref.uni-bayreuth.de/id/eprint/59023 |