Sobolev Norm Learning Rates for Conditional Mean Embeddings

Abstract

We develop novel learning rates for conditional mean embeddings by applying the theory of interpolation for reproducing kernel Hilbert spaces (RKHS). We derive explicit, adaptive learning rates for the sample estimator under the misspecifed setting, where the learning target is not smooth/bounded with respect to the input/output RKHSs. We demonstrate that in certain parameter regimes, we can achieve uniform convergence rates in the output RKHS. We hope our analyses will allow the much broader application of conditional mean embeddings to more complex ML/RL settings involving infinite dimensional RKHS and continuous state spaces.