English

NeuMC -- a package for neural sampling for lattice field theories

High Energy Physics - Lattice 2025-10-09 v1 Machine Learning

Abstract

We present the \texttt{NeuMC} software package, based on \pytorch, aimed at facilitating the research on neural samplers in lattice field theories. Neural samplers based on normalizing flows are becoming increasingly popular in the context of Monte-Carlo simulations as they can effectively approximate target probability distributions, possibly alleviating some shortcomings of the Markov chain Monte-Carlo methods. Our package provides tools to create such samplers for two-dimensional field theories.

Keywords

Cite

@article{arxiv.2503.11482,
  title  = {NeuMC -- a package for neural sampling for lattice field theories},
  author = {Piotr Bialas and Piotr Korcyl and Tomasz Stebel and Dawid Zapolski},
  journal= {arXiv preprint arXiv:2503.11482},
  year   = {2025}
}

Comments

42 pages, 15 figures, for associated code repository, see https://github.com/nmcmc/neumc.git

R2 v1 2026-06-28T22:20:44.787Z