Saved in:
Bibliographic Details
Main Authors: He, Jinchen, Jin, Xiao-Yong, Osborn, James C., Zhao, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.02018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917057808826368
author He, Jinchen
Jin, Xiao-Yong
Osborn, James C.
Zhao, Yong
author_facet He, Jinchen
Jin, Xiao-Yong
Osborn, James C.
Zhao, Yong
contents Critical slowing down, where autocorrelation grows rapidly near the continuum limit due to Hybrid Monte Carlo (HMC) moving through configuration space inefficiently, still challenges lattice gauge theory simulations. Combining neural field transformations with HMC (NTHMC) can reshape the energy landscape and accelerate sampling, but the choice of neural architectures has yet to be studied systematically. We evaluate NTHMC on a two-dimensional U(1) gauge theory, analyzing how it scales and transfers to larger volumes and smaller lattice spacing. Controlled comparisons let us isolate architectural contributions to sampling efficiency. Good designs can reduce autocorrelation and boost topological tunneling while maintaining favorable scaling. More broadly, our study highlights emerging design guides, such as wider receptive fields and channel-dependent activations, paving the way for systematic extensions to four-dimensional SU(3) gauge theory.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Field Transformations for Hybrid Monte Carlo: Architectural Design and Scaling
He, Jinchen
Jin, Xiao-Yong
Osborn, James C.
Zhao, Yong
High Energy Physics - Lattice
Critical slowing down, where autocorrelation grows rapidly near the continuum limit due to Hybrid Monte Carlo (HMC) moving through configuration space inefficiently, still challenges lattice gauge theory simulations. Combining neural field transformations with HMC (NTHMC) can reshape the energy landscape and accelerate sampling, but the choice of neural architectures has yet to be studied systematically. We evaluate NTHMC on a two-dimensional U(1) gauge theory, analyzing how it scales and transfers to larger volumes and smaller lattice spacing. Controlled comparisons let us isolate architectural contributions to sampling efficiency. Good designs can reduce autocorrelation and boost topological tunneling while maintaining favorable scaling. More broadly, our study highlights emerging design guides, such as wider receptive fields and channel-dependent activations, paving the way for systematic extensions to four-dimensional SU(3) gauge theory.
title Neural Field Transformations for Hybrid Monte Carlo: Architectural Design and Scaling
topic High Energy Physics - Lattice
url https://arxiv.org/abs/2511.02018