Search Results for author: Miguel Spinola

Found 1 papers, 0 papers with code

GNN-Assisted Phase Space Integration with Application to Atomistics

no code implementations20 Mar 2023 Shashank Saxena, Jan-Hendrik Bastek, Miguel Spinola, Prateek Gupta, Dennis M. Kochmann

As a remedy, we demonstrate that Graph Neural Networks, trained on Monte-Carlo data, can serve as a replacement for commonly used numerical quadrature rules, overcoming their deficiencies and significantly improving the accuracy.

Computational Efficiency

Cannot find the paper you are looking for? You can Submit a new open access paper.