Data-driven Random-feature Approximation of Koopman Generators of Nonlinear Continuous-time Systems (Q7414865)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

No description defined
Language Label Description Also known as
default for all languages
No label defined
    English
    Data-driven Random-feature Approximation of Koopman Generators of Nonlinear Continuous-time Systems
    No description defined

      Statements

      Data-driven Random-feature Approximation of Koopman Generators of Nonlinear Continuous-time Systems (English)
      0 references
      29 October 2026
      0 references
      cs.LG
      0 references
      math.NA
      0 references
      Ana Čukarska
      0 references
      Maximilian Gollwitzer
      0 references
      Viola Muning Li
      0 references
      Vladyslav Fediukov
      0 references
      Zahra Monfared
      0 references
      Felix Dietrich
      0 references
      We propose a data-driven random-feature method to learn a parsimonious representation for Koopman generators in nonlinear continuous-time systems, improving upon existing methods with a proven convergence guarantee. This allows for efficient learning of system dynamics from data and accurate forecasting and analysis.
      0 references
      Koopman Operators
      0 references
      Random Features
      0 references
      Continuous-Time Systems
      0 references
      Galerkin Methods
      0 references

      Identifiers

      0 references