Johannes Müller
5 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(7)
🌉
Interdisciplinary Bridge
Conferences
ICML (3)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
physics-informed neural network
(2)
automatic differentiation
(1)
natural gradient
(1)
natural gradient descent
(1)
riemannian metric
(1)
second-order optimization
(1)
optimization algorithm
(1)
gauss-newton method
(1)
approximate curvature
(1)
deep ritz method
(1)
kronecker factorization
(1)
hessian-induced riemannian metric
(1)
neural network optimization
(1)
kronecker factored approximate curvature
(1)
Papers
Embedding Safety into RL: A New Take on Trust Region Methods
ICML 2025
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
NIPS 2024
Position: Optimization in SciML Should Employ the Function Space Geometry
ICML 2024
Achieving High Accuracy with PINNs via Energy Natural Gradient Descent
ICML 2023
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs
ICLR 2022