Gauge covariant neural network for quarks and gluons
Year: 2025
Type: article
Abstract: We propose gauge covariant neural networks along with a specialized training algorithm for lattice QCD, designed to handle realistic quarks and gluons in four-dimensional space-time. We show that the smearing procedure can be interpreted as an extended version of residual neural networks with fixed parameters. To demonstrate the applicability of our neural networks, we develop a self-learning hybrid Monte Carlo algorithm in the context of two-color QCD, yielding outcomes consistent with those from the conventional hybrid Monte Carlo approach.
Authors: Yuki Nagai, Akio Tomiya
Language: English
Subfield: Nuclear and High Energy Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1141117319, G3479324779, G3720736218, Phase structure of gauge theories via digital quantum computers, G3978147871, Study of high performance and accuracy eigenvalue solvers for quantum many-body systems, G4800436002, G5720537884, High Performance Computing for Quantum Model Simulations on Exascale Computers, G6530602596, Self-learning continuous-time Monte Carlo method in strongly correlated systems, G6856085930, G781142722, Effective models constructed by neural networks with symmetries
OpenAlex ID: W4409132126