167 citations · 1.3k across the 78 of their papers we have counts for
87 papers
Preconditioned Physics-Informed Neural Operator Training
Shizheng Wen, Siddhartha Mishra, Marius Zeinhofer
Neural operators are typically trained in a supervised fashion, which requires a dataset to be generated with a classical solver. Training them physics-informed, i.e., purely from…
Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States
Hang Zhang, Victor Armegioiu, Juan Carrasquilla +4
Deep learning offers a powerful approach to quantum many-body problems via neural network wavefunctions, but their optimization remains a severe bottleneck. Existing optimization m…
Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
Janne Perini, Rafael Bischof, Moab Arar +4
Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but their current computational cost m…
Gauss-Newton Natural Gradient Descent for Shape Learning
James King, Arturs Berzins, Siddhartha Mishra +1
We explore the use of the Gauss-Newton method for optimization in shape learning, including implicit neural surfaces and geometry-informed neural networks. The method addresses key…
Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science
Levi Lingsch, Georgios Kissas, Johannes Jakubik +1
Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and ge…
Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm
Shizheng Wen, Mingyuan Chi, Tianwei Yu +5
We present a unified algorithmic framework for the numerical solution, constrained optimization, and physics-informed learning of PDEs with a variational structure. Our framework i…