Research Group Felix Dietrich
Felix Dietrich
Prof. Dr.
Collaborating PI
Felix Dietrich
holds a professorship for Physics-Enhanced Machine Learning at TU Munich.
His research focus on the analysis and development of numerical algorithms for machine learning. This covers algorithms to enable, accelerate, and optimize simulation and analysis of complex dynamical systems, as well as nonlinear manifold learning techniques, including data-driven approximations of Koopman and Laplace operators. Recently, his group has also worked on energy-efficient training of neural networks inspired by random feature modeling.
Team members @MCML
PhD Students
Erik Lien Bolager
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Iryna Burak
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Ana Cukarska
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Chinmay Datar
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Atamert Rahma
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Qing Sun
→ Group Felix Dietrich
Physics-enhanced Machine Learning
Recent News @MCML
Publications @MCML
2026
Fast training of accurate physics-informed neural networks without gradient descent.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. Oral Presentation. To be published. Preprint available. arXiv
Rapid training of Hamiltonian graph networks without gradient descent.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. arXiv
Dictionary learning for Kernel EDMD.
Preprint (Apr. 2026). arXiv
On the algebra of Koopman eigenfunctions and on some of their infinities.
Preprint (Apr. 2026). arXiv
Graph Neural Networks for Full Waveform Inversion.
Preprint (Jan. 2026). URL
2025
Neural network-based singularity detection and applications.
Preprint (Sep. 2025). arXiv
Systematic Construction of Continuous-Time Neural Networks for Linear Dynamical Systems.
SIAM Journal on Scientific Computing 47.4. Jul. 2025. DOI
©all images: LMU | TUM
2024-12-27 - Last modified: 2026-04-22