Program

Reproducing kernel Hilbert spaces (RKHSs): Motivation: supervised learning with linear rules in feature space.

Reproducing kernel Hilbert spaces (RKHSs): Finite dimensional RKHSs. General RKHSs and examples

RKHSs for machine learning: Supervised learning with RKHSs: uniform concentration, representer theorem, and universal consistency.

RKHSs for machine learning: Approximation based on random features. 

RKHSs for machine learning: Kernel mean embedding and maximum mean discrepancy.