English

LeapfrogLayers: A Trainable Framework for Effective Topological Sampling

High Energy Physics - Lattice 2022-01-17 v2 Machine Learning

Abstract

We introduce LeapfrogLayers, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D U(1)U(1) lattice gauge theory. We show an improvement in the integrated autocorrelation time of the topological charge when compared with traditional HMC, and look at how different quantities transform under our model. Our implementation is open source, and is publicly available on github at https://github.com/saforem2/l2hmc-qcd.

Keywords

Cite

@article{arxiv.2112.01582,
  title  = {LeapfrogLayers: A Trainable Framework for Effective Topological Sampling},
  author = {Sam Foreman and Xiao-Yong Jin and James C. Osborn},
  journal= {arXiv preprint arXiv:2112.01582},
  year   = {2022}
}

Comments

10 pages, 12 figures, presented at the 38th International Symposium on Lattice Field Theory, LATTICE2021 26th-30th July, 2021, Zoom/Gather @ Massachusetts Institute of Technology

R2 v1 2026-06-24T08:02:23.883Z