17 papers
Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
Maximiliano Hertel, Ilja Klebanov, Manuel Schaller +1
Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning, appearing in n…
Koopman meets input-output data: Data-driven output-feedback control of nonlinear systems with closed-loop guarantees
Robin Strässer, Julian Berberich, Manuel Schaller +2
Data-driven control of nonlinear systems from input-output measurements remains a fundamental challenge, as existing approaches with rigorous closed-loop guarantees predominantly r…
Koopman for stochastic dynamics: error bounds for kernel extended dynamic mode decomposition
Maximiliano Hertel, Friedrich M. Philipp, Manuel Schaller +1
We prove -error bounds for kernel extended dynamic mode decomposition (kEDMD) approximants of the Koopman operator for stochastic dynamical systems. To this end, we estab…
Data-driven Model Predictive Control: Asymptotic Stability despite Approximation Errors exemplified in the Koopman framework
Irene Schimperna, Karl Worthmann, Manuel Schaller +2
In this paper, we analyze stability of nonlinear model predictive control (MPC) using data-driven surrogate models in the optimization step. First, we establish asymptotic stabilit…
Spatial exponential decay of perturbations in optimal control of general evolution equations
Simone Göttlich, Benedikt Oppeneiger, Manuel Schaller +1
We analyze the robustness of optimally controlled evolution equations with respect to spatially localized perturbations. We prove that if the involved operators are domain-uniforml…
An overview of Koopman-based control: From error bounds to closed-loop guarantees
Robin Strässer, Karl Worthmann, Igor MeziÄ +3
Controlling nonlinear dynamical systems remains a central challenge in a wide range of applications, particularly when accurate first-principle models are unavailable. Data-driven…