collaborators

5 papers

quant-ph2026

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…

cs.LG2026

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks

Anas Jnini, Elham Kiyani, Khemraj Shukla +5

Efficient and robust optimization is essential for neural networks, enabling scientific machine learning models to converge rapidly to very high accuracy -- faithfully capturing co…

cs.LG2026

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…

cs.LG2025

Collapsing Taylor Mode Automatic Differentiation

Felix Dangel, Tim Siebert, Marius Zeinhofer +1

Computing partial differential equation (PDE) operators via nested backpropagation is expensive, yet popular, and severely restricts their utility for scientific machine learning.…

cs.LG2025

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization

Andrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager +1

Natural gradient methods significantly accelerate the training of Physics-Informed Neural Networks (PINNs), but are often prohibitively costly. We introduce a suite of techniques t…