Sobolev Norm Learning Rates for Conditional Mean Embeddings
This enables broader application of conditional mean embeddings to complex ML/RL settings with infinite-dimensional RKHSs and continuous state spaces.
The paper tackles the problem of deriving learning rates for conditional mean embeddings in misspecified settings where the target operator is not Hilbert-Schmidt or bounded, achieving explicit, adaptive convergence rates and uniform convergence in certain parameter regimes.
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 convergence rates for the sample estimator under the misspecifed setting, where the target operator is not Hilbert-Schmidt or 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 RKHSs and continuous state spaces.