English

Deep Learning of Fermion Sign Fluctuations

High Energy Physics - Lattice 2023-07-11 v2

Abstract

We describe a procedure for alleviating the fermion sign problem in which phase fluctuations are explicitly subtracted from the Boltzmann factor. Several ans\"atze for fluctuations are designed and compared. In the absence of a sufficiently high-quality ansatz, a neural network can be trained to parameterize the fluctuations. Demonstrating on the staggered Thirring model in 1+11+1 dimensions, we examine the performance of this method as deeper neural networks are used, and in conjunction with the well-studied contour deformation methods.

Keywords

Cite

@article{arxiv.2212.14606,
  title  = {Deep Learning of Fermion Sign Fluctuations},
  author = {Scott Lawrence and Yukari Yamauchi},
  journal= {arXiv preprint arXiv:2212.14606},
  year   = {2023}
}

Comments

10 pages, 5 figures