Representer Theorem for Learning Koopman Operators

doi:10.1109/TAC.2023.3242325

Representer Theorem for Learning Koopman Operators

2023-05-01

4

OA

AI

M

Mohammad Khosravi *

DOI：10.1109/TAC.2023.3242325

Original

Original request for help

Save

Abstract

En 中文

In this work, we consider the problem of learning the Koopman operator for discrete-time autonomous systems. The learning problem is formulated as a generic constrained regularized empirical loss minimization in the infinite-dimensional space of linear operators. We show that a representer theorem holds for the introduced learning problem under certain but general conditions, which allows convex reformulation of the problem in a specific finite-dimensional space without any approximation and loss of precision. We discuss the inclusion of various forms of regularization and constraints in the learning problem, such as the operator norm, the Frobenius norm, the operator rank, the nuclear norm, and the stability. Subsequently, we derive the corresponding equivalent finite-dimensional problem. Furthermore, we demonstrate the connection between the proposed formulation and the extended dynamic mode decomposition. We present several numerical examples to illustrate the theoretical results and verify the performance of regularized learning of the Koopman operators.

Keywords:

Nonlinear dynamical systems

Kernel

Hilbert space

Trajectory

Stability criteria

Numerical stability

Minimization

Koopman operators

learning

representer theorem

Representer Theorem for Learning Koopman Operators

Abstract

Journal

Organization