Seminar: Discovering Dynamics with KANs: Algorithms and Error Estimation

Seminar| Institute of Mathematical Sciences

Time:Friday, June 20th, 2025,10:00-11:00

Abstract:In this talk, we propose a framework that integrates Kolmogorov–Arnold Networks (KANs) with LMMs for the discovery and approximation of dynamical systems' vector fields. Specifically, we begin by establishing error bounds for two-layer B-spline KANs when approximating the governing functions of dynamical systems. Leveraging the approximation capabilities of KANs, we demonstrate that for certain families of LMMs, the total error is constrained within a specific range that accounts for both the method's step size and the network's approximation accuracy.