Folgen
Johannes Müller
Titel
Zitiert von
Zitiert von
Jahr
Error estimates for the deep Ritz method with boundary penalty
J Müller, M Zeinhofer
Mathematical and Scientific Machine Learning, 215-230, 2022
42*2022
Deep Ritz revisited
J Müller, M Zeinhofer
DeepDiffEq workshop at ICLR 2020, 2020
302020
Achieving High Accuracy with PINNs via Energy Natural Gradients
J Müller, M Zeinhofer
International Conference on Machine Learning, 25471-25485, 2023
272023
Uniform Convergence Guarantees for the Deep Ritz Method for Nonlinear Problems
P Dondl, J Müller, M Zeinhofer
Advances in Continuous and Discrete Models, 2022
152022
Notes on Exact Boundary Values in Residual Minimisation
J Müller, M Zeinhofer
Mathematical and Scientific Machine Learning, 231-240, 2022
142022
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs
G Montúfar, J Müller
International Conference of Learning Representations, 2022
11*2022
Invariance properties of the natural gradient in overparametrised systems
J van Oostrum, J Müller, N Ay
Information geometry 6 (1), 51-67, 2023
92023
Geometry and convergence of natural policy gradient methods
J Müller, G Montúfar
Information Geometry 7 (Suppl 1), 485-523, 2024
72024
On the space-time expressivity of ResNets
J Müller
DeepDiffEq workshop at ICLR 2020, 2020
7*2020
Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space
J Müller, G Montúfar
5th Multi-disciplinary Conference on Reinforcement Learning and Decision …, 2022
52022
Universal flow approximation with deep residual networks
J Müller
University of Freiburg, 2019
32019
Position: Optimization in SciML Should Employ the Function Space Geometry
J Müller, M Zeinhofer
Forty-first International Conference on Machine Learning, 2024
2*2024
Geometry of Optimization in Markov Decision Processes and Neural Network-Based PDE Solvers
J Müller
Dissertation, 2024
22024
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
F Dangel, J Müller, M Zeinhofer
arXiv preprint arXiv:2405.15603, 2024
12024
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients
J Müller, S Çaycı, G Montúfar
arXiv preprint arXiv:2403.19448, 2024
12024
Algebraic Optimization of Sequential Decision Problems
M Dressler, M Garrote-López, G Montúfar, J Müller, K Rose
Journal of Symbolic Computation 121, 2022
12022
Essentially Sharp Estimates on the Entropy Regularization Error in Discrete Discounted Markov Decision Processes
J Müller, S Cayci
arXiv preprint arXiv:2406.04163, 2024
2024
Parameter estimation and consistency for discrete determinantal point processes
J Müller
University of Warwick, 2018
2018
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–18