English

Machine Learning Line Bundle Connections

High Energy Physics - Theory 2022-03-09 v1

Abstract

We study the use of machine learning for finding numerical hermitian Yang-Mills connections on line bundles over Calabi-Yau manifolds. Defining an appropriate loss function and focusing on the examples of an elliptic curve, a K3 surface and a quintic threefold, we show that neural networks can be trained to give a close approximation to hermitian Yang-Mills connections.

Keywords

Cite

@article{arxiv.2110.12483,
  title  = {Machine Learning Line Bundle Connections},
  author = {Anthony Ashmore and Rehan Deen and Yang-Hui He and Burt A. Ovrut},
  journal= {arXiv preprint arXiv:2110.12483},
  year   = {2022}
}
R2 v1 2026-06-24T07:08:22.801Z