Learning rates for regularized least squares ranking algorithm
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Pages (from-to) | 815-836 |
| Journal / Publication | Analysis and Applications |
| Volume | 15 |
| Issue number | 6 |
| Online published | 11 May 2017 |
| Publication status | Published - Nov 2017 |
Link(s)
Abstract
The ranking problem aims at learning real-valued functions to order instances, which has attracted great interest in statistical learning theory. In this paper, we consider the regularized least squares ranking algorithm within the framework of reproducing kernel Hilbert space. In particular, we focus on analysis of the generalization error for this ranking algorithm, and improve the existing learning rates by virtue of an error decomposition technique from regression and Hoeffding's decomposition for U-statistics.
Research Area(s)
- approximation error, covering number, generalization bound, Ranking algorithm, U-statistics
Citation Format(s)
Learning rates for regularized least squares ranking algorithm. / Zhao, Yulong; Fan, Jun; Shi, Lei.
In: Analysis and Applications, Vol. 15, No. 6, 11.2017, p. 815-836.
In: Analysis and Applications, Vol. 15, No. 6, 11.2017, p. 815-836.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
