PoS - Proceedings of Science
Volume 453 - The 40th International Symposium on Lattice Field Theory (LATTICE2023) - Software Development and Machines
NeuLat: a toolbox for neural samplers in lattice field theories
K.A. Nicoli*, C. Anders, L. Funcke, K. Jansen, S. Nakajima and P. Kessel
Full text: pdf
Pre-published on: December 27, 2023
Published on: November 06, 2024
Abstract
The application of normalizing flows for sampling in lattice field theory has garnered considerable attention in recent years. Despite the growing community at the intersection of machine learning (ML) and lattice field theory, there is currently a lack of a software package that facilitates efficient software development for new ideas in this field. We present NeuLat, a fully customizable software package that unifies recent advances in the fast-growing field of deep generative models for lattice field theory in a single software library. NeuLat is designed to be modular, supports a variety of lattice field theories as well as normalizing flow architectures, and is easily extensible.
We believe that NeuLat has the potential to considerably simplify the application and benchmarking of ML methods for lattice quantum field theories and beyond
DOI: https://doi.org/10.22323/1.453.0286
How to cite

Metadata are provided both in "article" format (very similar to INSPIRE) as this helps creating very compact bibliographies which can be beneficial to authors and readers, and in "proceeding" format which is more detailed and complete.

Open Access
Creative Commons LicenseCopyright owned by the author(s) under the term of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.