Koopman operator, geometry, and learning of dynamical systems

DOI10.1090/NOTI2306MaRDI QIDQ5029862zbMATH OpenOpenAlexFDO

Authors Igor Mezić

Publication date 15 February 2022

Published in Notices of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2010.05377

zbMATH Keywords

Koopman operatorsgeometry of state spaceMori-Zwanzig type representations

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation methods and numerical treatment of dynamical systems (37M99)

Abstract: We provide a framework for learning of dynamical systems rooted in the concept of representations and Koopman operators. The interplay between the two leads to the full description of systems that can be represented linearly in a finite dimension, based on the properties of the Koopman operator spectrum. The geometry of state space is connected to the notion of representation, both in the linear case - where it is related to joint level sets of eigenfunctions - and in the nonlinear representation case. As shown here, even nonlinear finite-dimensional representations can be learned using the Koopman operator framework, leading to a new class of representation eigenproblems. The connection to learning using neural networks is given. An extension of the Koopman operator theory to "static" maps between different spaces is provided. The effect of the Koopman operator spectrum on Mori-Zwanzig type representations is discussed.

Recommendations

• Time-delay observables for Koopman: theory and applications
• Applied Koopmanism
• On Matching, and Even Rectifying, Dynamical Systems through Koopman Operator Eigenfunctions
• Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability
• scientific article; zbMATH DE number 7568220

Cited in

(15)

• Generative stochastic modeling of strongly nonlinear flows with non-Gaussian statistics
• Learning latent dynamics for partially observed chaotic systems
• Reduced Order Characterization of Nonlinear Oscillations Using an Adaptive Phase-Amplitude Coordinate Framework
• Data-driven reduced order models using invariant foliations, manifolds and autoencoders
• Learning Theory for Dynamical Systems
• Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics
• Rigorous data‐driven computation of spectral properties of Koopman operators for dynamical systems
• Learning Koopman eigenfunctions of stochastic diffusions with optimal importance sampling and ISOKANN
• Residual dynamic mode decomposition: robust and verified Koopmanism
• Data-driven learning for the Mori-Zwanzig formalism: a generalization of the Koopman learning framework
• On the Koopman operator of algorithms
• Regression-Based Projection for Learning Mori–Zwanzig Operators
• Spectral Properties of Pullback Operators on Vector Bundles of a Dynamical System
• The mpEDMD Algorithm for Data-Driven Computations of Measure-Preserving Dynamical Systems
• Manifold learning for data-driven dynamical system analysis

This page was built for publication: Koopman operator, geometry, and learning of dynamical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5029862)