You can find all of my works on arXiv.

Preprints

3. Anas Jnini, Elham Kiyani, Khemraj Shukla, Jorge Urban, Nazanin Daryakenari, Johannes Muller, Marius Zeinhofer, George Karniadakis. Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks. arXiv preprint arXiv:2604.05230 (2026). [Access paper]
4. Victor Armegioiu, Juan Carrasquilla, Siddhartha Mishra, Johannes Müller, Jannes Nys, Marius Zeinhofer, Hang Zhang. Functional Neural Wavefunction Optimization. arXiv preprint arXiv:2507.10835 (2025). [Access paper]
5. Jingtong Sun, Julius Berner, Lorenz Richter, Marius Zeinhofer, Johannes Müller, Kamyar Azizzadenesheli, Anima Anandkumar. Dynamical measure transport and neural PDE solvers for sampling. arXiv preprint arXiv:2407.07873 (2024). [Access paper]

Publications

18. Johannes Müller, Semih Cayci. Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes. Information and Inference: A Journal of the IMA (2026). [Access paper]
19. Jonas Nießen, Johannes Müller. Non-asymptotic analysis of projected gradient descent for physics-informed neural networks. International Workshop of Scientific Machine Learning: Emerging Topics (2026). [Access paper]
20. Johannes Müller, Semih Çayci, Guido Montúfar. Fisher–Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients. SIAM Journal on Optimization (2025). [Access paper]
21. Nikola Milosevic, Johannes Müller, Nico Scherf. Embedding safety into rl: A new take on trust region methods. ICML 2025 (2025). [Access paper]
22. Nikola Milosevic, Johannes Müller, Nico Scherf. Central path proximal policy optimization. The Exploration in AI Today Workshop at ICML 2025 (2025). [Access paper]
23. Johannes Müller, Marius Zeinhofer. Position: Optimization in SciML Should Employ the Function Space Geometry. Forty-first International Conference on Machine Learning (2024). [Access paper]
24. Felix Dangel, Johannes Müller, Marius Zeinhofer. Kronecker-factored approximate curvature for physics-informed neural networks. Advances in Neural Information Processing Systems (NeurIPS) (2024). [Access paper]
25. Johannes Müller, Guido Montúfar. Geometry and convergence of natural policy gradient methods. Information Geometry (2024). [Access paper]
26. Jesse Oostrum, Johannes Müller, Nihat Ay. Invariance properties of the natural gradient in overparametrised systems. Information geometry (2023). [Access paper]
27. Johannes Müller, Marius Zeinhofer. Achieving High Accuracy with PINNs via Energy Natural Gradients. International Conference on Machine Learning (2023). [Access paper]
28. Patrick Dondl, Johannes Müller, Marius Zeinhofer. Uniform Convergence Guarantees for the Deep Ritz Method for Nonlinear Problems. Advances in Continuous and Discrete Models (2022). [Access paper]
29. Guido Montúfar, Johannes Müller. The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs. International Conference of Learning Representations (2022). [Access paper]
30. Johannes Müller, Guido Montúfar. Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space. 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022) (2022). [Access paper]
31. Johannes Müller, Marius Zeinhofer. Notes on Exact Boundary Values in Residual Minimisation. Mathematical and Scientific Machine Learning (2022). [Access paper]
32. Johannes Müller, Marius Zeinhofer. Error estimates for the deep Ritz method with boundary penalty. Mathematical and Scientific Machine Learning (2022). [Access paper]
33. Mareike Dressler, Marina Garrote-López, Guido Montúfar, Johannes Müller, Kemal Rose. Algebraic Optimization of Sequential Decision Problems. Journal of Symbolic Computation (2022). [Access paper]
34. Johannes Müller. On the space-time expressivity of ResNets. DeepDiffEq workshop at ICLR 2020 (2020). [Access paper]
35. Johannes Müller, Marius Zeinhofer. Deep Ritz revisited. DeepDiffEq workshop at ICLR 2020 (2020). [Access paper]