Mercer Theorem and Feature Maps
Lorenzo Rosasco


We introduce a particularly useful family of hypothesis spaces called Reproducing Kernel Hilbert Spaces (RKHS) that have a key role in the theory of learning. We first provide the necessary background in functional analysis and then define RKHS using the reproducing property. We then derive the general solution of Tikhonov regularization in RKHS.


Slides for this lecture: PDF.

Suggested Reading