GomalizingFlow.jl: A Julia package for Flow-based sampling algorithm for lattice field theory
Abstract
GomalizingFlow.jl: is a package to generate configurations for quantum field theory on the lattice using the flow based sampling algorithm in Julia programming language. This software serves two main purposes: to accelerate research of lattice QCD with machine learning with easy prototyping, and to provide an independent implementation to an existing public Jupyter notebook in Python/PyTorch. GomalizingFlow.jl implements, the flow based sampling algorithm, namely, RealNVP and Metropolis-Hastings test for two dimension and three dimensional scalar field, which can be switched by a parameter file. HMC for that theory also implemented for comparison. This package has Docker image, which reduces effort for environment construction. This code works both on CPU and NVIDIA GPU.
Keywords
Cite
@article{arxiv.2208.08903,
title = {GomalizingFlow.jl: A Julia package for Flow-based sampling algorithm for lattice field theory},
author = {Akio Tomiya and Satoshi Terasaki},
journal= {arXiv preprint arXiv:2208.08903},
year = {2023}
}
Comments
15 pages, 2 figures