Johannes Müller

Johannes Müller

He/him
Working on the mathematical foundations of learning

You can find all of my works on arXiv.

Preprints

  1. Benjamin Gess, Johannes Müller. The Advective Fisher-Rao Geometry of Deterministic Measure Transport. arXiv preprint arXiv:2608.12111 (2026). [Access paper]
  2. Hang Zhang, Victor Armegioiu, Juan Carrasquilla, Siddhartha Mishra, Johannes Müller, Jannes Nys, Marius Zeinhofer. Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States. arXiv preprint arXiv:2606.07825 (2026). [Access paper]
  3. 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]
  4. 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

  1. Johannes Müller, Semih Çayci. Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes. Information and Inference: A Journal of the IMA (2026). [Access paper]
  2. Jonas Nießen, Johannes Müller. Non-asymptotic analysis of projected gradient descent for physics-informed neural networks. Scientific Machine Learning: Emerging Topics (SEMA SIMAI Springer Series) (2026). [Access paper]
  3. Anas Jnini, Elham Kiyani, Khemraj Shukla, Jorge F. Urban, Nazanin Ahmadi Daryakenari, Johannes Müller, Marius Zeinhofer, George Em Karniadakis. Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks. Computer Methods in Applied Mechanics and Engineering (2026). [Access paper]
  4. 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]
  5. Nikola Milosevic, Johannes Müller, Nico Scherf. Embedding Safety into RL: A New Take on Trust Region Methods. International Conference on Machine Learning (ICML) (2025). [Access paper]
  6. Johannes Müller, Marius Zeinhofer. Position: Optimization in SciML Should Employ the Function Space Geometry. International Conference on Machine Learning (ICML) (2024). [Access paper]
  7. 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]
  8. Johannes Müller, Guido Montúfar. Geometry and convergence of natural policy gradient methods. Information Geometry (2024). [Access paper]
  9. Mareike Dressler, Marina Garrote-López, Guido Montúfar, Johannes Müller, Kemal Rose. Algebraic optimization of sequential decision problems. Journal of Symbolic Computation (2024). [Access paper]
  10. Jesse van Oostrum, Johannes Müller, Nihat Ay. Invariance properties of the natural gradient in overparametrised systems. Information geometry (2023). [Access paper]
  11. Johannes Müller, Marius Zeinhofer. Achieving High Accuracy with PINNs via Energy Natural Gradient Descent. International Conference on Machine Learning (ICML) (2023). [Access paper]
  12. 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]
  13. Johannes Müller, Guido Montúfar. The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs. International Conference on Learning Representations (ICLR) (2022). [Access paper]
  14. Johannes Müller, Marius Zeinhofer. Notes on Exact Boundary Values in Residual Minimisation. Mathematical and Scientific Machine Learning (MSML) (2022). [Access paper]
  15. Johannes Müller, Marius Zeinhofer. Error Estimates for the Deep Ritz Method with Boundary Penalty. Mathematical and Scientific Machine Learning (MSML) (2022). [Access paper]

Workshop Papers

  1. Nikola Milosevic, Johannes Müller, Nico Scherf. Central Path Proximal Policy Optimization. Exploration in AI Today Workshop at ICML 2025 (2025). [Access paper]
  2. Johannes Müller, Guido Montúfar. Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space. Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2022 (2022). [Access paper]
  3. Johannes Müller. On the space-time expressivity of ResNets. Workshop on Integration of Deep Neural Models and Differential Equations at ICLR 2020 (2020). [Access paper]
  4. Johannes Müller, Marius Zeinhofer. Deep Ritz revisited. Workshop on Integration of Deep Neural Models and Differential Equations at ICLR 2020 (2020). [Access paper]