Deep Learning Hamiltonian Monte Carlo
High Energy Physics - Lattice
2021-05-10 v1 Statistical Mechanics
Machine Learning
Machine Learning
Abstract
We generalize the Hamiltonian Monte Carlo algorithm with a stack of neural network layers and evaluate its ability to sample from different topologies in a two dimensional lattice gauge theory. We demonstrate that our model is able to successfully mix between modes of different topologies, significantly reducing the computational cost required to generated independent gauge field configurations. Our implementation is available at https://github.com/saforem2/l2hmc-qcd .
Cite
@article{arxiv.2105.03418,
title = {Deep Learning Hamiltonian Monte Carlo},
author = {Sam Foreman and Xiao-Yong Jin and James C. Osborn},
journal= {arXiv preprint arXiv:2105.03418},
year = {2021}
}
Comments
8 pages, 7 figures, Published as a workshop paper at ICLR 2021 SimDL Workshop