Data-driven methods for partial differential equations

Session

Invited talks 2

Mar 2, 2026, 3:15 PM

Room 1.067 (Math Building (20.30), Karlsruhe Institute of Technology)

Conveners

Invited talks 2: Learning dynamical systems (Speaker: Gottschalk, Boyer)

• Mathias Trabs (KIT)

18. When do World Models Successfully Learn Dynamic Systems?

Hanno Gottschalk (TU Berlin)

3/2/26, 3:15 PM

Invited talk

In this work, we explore the use of compact latent representations with learned time dynamics ('World Models') to simulate physical systems. Drawing on concepts from control theory, we propose a theoretical framework that explains why projecting time slices into a low-dimensional space and then concatenating to form a history ('Tokenization') is so effective at learning physics datasets, and...

13. A statistical tour of physics-informed learning

Prof. Claire Boyer (Université Paris-Saclay)

3/2/26, 4:00 PM

Invited talk

We will begin by discussing the limitations inherent in the training of Physics-Informed Neural Networks (PINNs), which, despite their conceptual appeal, often face practical challenges (such as convergence issues, sensitivity to hyperparameters, and the need of large data volume). In a second step, we will recast and characterize the problem of physics-informed learning as a kernel method....