𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Derivative reproducing properties for kernel methods in learning theory

✍ Scribed by Ding-Xuan Zhou


Publisher
Elsevier Science
Year
2008
Tongue
English
Weight
175 KB
Volume
220
Category
Article
ISSN
0377-0427

No coin nor oath required. For personal study only.

✦ Synopsis


The regularity of functions from reproducing kernel Hilbert spaces (RKHSs) is studied in the setting of learning theory. We provide a reproducing property for partial derivatives up to order s when the Mercer kernel is C 2s . For such a kernel on a general domain we show that the RKHS can be embedded into the function space C s . These observations yield a representer theorem for regularized learning algorithms involving data for function values and gradients. Examples of Hermite learning and semi-supervised learning penalized by gradients on data are considered.


📜 SIMILAR VOLUMES