Machine-learned RG-improved gauge actions and classically perfect gradient flows

Abstract

Extracting continuum properties of quantum field theories from discretized spacetime is challenging due to lattice artifacts. Renormalization-group (RG)-improved lattice actions can preserve continuum properties, but are in general difficult to parameterize. Machine learning (ML) with gauge-equivariant convolutional neural networks provides a way to efficiently describe such actions. We test a machine-learned RG-improved lattice gauge action, the classically perfect fixed-point (FP) action, for four-dimensional SU(3) gauge theory through Monte Carlo simulations. We establish that the gradient flow of the FP action is free of tree-level discretization effects to all orders in the lattice spacing, making it classically perfect. This allows us to test the quality of improvement of the FP action, without introducing additional artifacts. We find that discretization effects in gradient-flow observables are highly suppressed and less than 1% up to lattice spacings of 0.14 fm, allowing continuum physics to be extracted from coarse lattices. The quality of improvement achieved motivates the use of the FP action in future gauge theory studies. The advantages of ML-based parameterizations also highlight the possibility of realizing quantum perfect actions in lattice gauge theory.

12 pages, 4 tables, 6 figures; updated to published version

References in corpus (25)

• Properties and uses of the Wilson flow in lattice QCD
• FLAG Review 2021
• Perturbative analysis of the gradient flow in non-abelian gauge theories
• High-precision scale setting in lattice QCD
• Infinite N phase transitions in continuum Wilson loop operators
• Critical slowing down and error analysis in lattice QCD simulations
• Equivariant flow-based sampling for lattice gauge theory
• Testing and tuning symplectic integrators for Hybrid Monte Carlo algorithm in lattice QCD
• The lattice gradient flow at tree-level and its improvement
• Symanzik improvement of the gradient flow in lattice gauge theories
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions
• The perturbative QCD gradient flow to three loops
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Topological susceptibility at $T>T_{\mathrm{c}}$ from master-field simulations of the SU(3) gauge theory
• Learning Trivializing Gradient Flows for Lattice Gauge Theories
• Continuous renormalization group $\beta$ function from lattice simulations
• The gradient flow coupling at high-energy and the scale of SU(3) Yang-Mills theory
• Power corrections from decoupling of the charm quark
• Determination of ${\alpha }_s(m_Z)$ by the non-perturbative decoupling method
• A new method for the beta function in the chiral symmetry broken phase
• $\Lambda$ parameter of the SU(3) Yang-Mills theory from the continuous $\beta$ function
• Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
• Static force from generalized Wilson loops on the lattice using the gradient flow
• Non-Perturbative Trivializing Flows for Lattice Gauge Theories

Cited by in corpus (4)

• Approximating Grassmann valued path integrals with radial basis function neural networks
• Lattice fermion formulation via Physics-Informed Neural Networks: Ginsparg-Wilson relation and Overlap fermions
• Wilson loops with neural networks
• Scale setting of SU($N$) Yang--Mills theory, topology and large-$N$ volume independence