Deep Learning Hamiltonian Monte Carlo

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 .

arXiv comment8 pages, 7 figures, Published as a workshop paper at ICLR 2021 SimDL Workshop

References in corpus (8)

• Horovod: fast and easy distributed deep learning in TensorFlow
• Equivariant flow-based sampling for lattice gauge theory
• Sampling using $SU(N)$ gauge equivariant flows
• Normalizing Flows on Tori and Spheres
• NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
• Lattice gauge equivariant convolutional neural networks
• Introduction to Normalizing Flows for Lattice Field Theory
• Generative models for sampling of lattice field theories

Cited by in corpus (3)

• Machine Learning in Nuclear Physics
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Applications of flow models to the generation of correlated lattice QCD ensembles