Develops a nonparametric sparse online algorithm to learn the Koopman operator iteratively via stochastic approximation with explicit complexity control and convergence guarantees in misspecified RKHS settings via conditional mean embeddings.
Following Section 4, we make the following assumption on the regularity ofK, which encodes the regularity of the Markov kernel
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Nonparametric Sparse Online Learning of the Koopman Operator
Develops a nonparametric sparse online algorithm to learn the Koopman operator iteratively via stochastic approximation with explicit complexity control and convergence guarantees in misspecified RKHS settings via conditional mean embeddings.