Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network

Abstract

Fixed point lattice actions are designed to have continuum classical properties unaffected by discretization effects and reduced lattice artifacts at the quantum level. They provide a possible way to extract continuum physics with coarser lattices, thereby allowing one to circumvent problems with critical slowing down and topological freezing toward the continuum limit. A crucial ingredient for practical applications is to find an accurate and compact parametrization of a fixed point action, since many of its properties are only implicitly defined. Here we use machine learning methods to revisit the question of how to parametrize fixed point actions. In particular, we obtain a fixed point action for four-dimensional SU(3) gauge theory using convolutional neural networks with exact gauge invariance. The large operator space allows us to find superior parametrizations compared to previous studies, a necessary first step for future Monte Carlo simulations and scaling studies.

22 pages, 15 figures, 6 tables; updated to published version

References in corpus (20)

• A high-bias, low-variance introduction to Machine Learning for physicists
• FLAG Review 2021
• Trivializing maps, the Wilson flow and the HMC algorithm
• Critical slowing down and error analysis in lattice QCD simulations
• Lattice QCD without topology barriers
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Equivariant flow-based sampling for lattice gauge theory
• Sampling using $SU(N)$ gauge equivariant flows
• Quenched spectroscopy with fixed-point and chirally improved fermions
• The construction of generalized Dirac operators on the lattice
• Fixed Point Gauge Actions with Fat Links: Scaling and Glueballs
• Master-field simulations of O(a)-improved lattice QCD: Algorithms, stability and exactness
• Mapping distinct phase transitions to a neural network
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Machine-learning physics from unphysics: Finding deconfinement temperature in lattice Yang-Mills theories from outside the scaling window
• Learning Trivializing Gradient Flows for Lattice Gauge Theories
• Diffusion Models as Stochastic Quantization in Lattice Field Theory
• Simulating Full QCD with the Fixed Point Action
• New results on cut-off effects in spectroscopy with the fixed point action
• 2+1 Flavor QCD simulated in the epsilon-regime in different topological sectors

Cited by in corpus (6)

• FLAG Review 2024
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Deep learning lattice gauge theories
• Gauge covariant neural network for quarks and gluons
• Machine-learned RG-improved gauge actions and classically perfect gradient flows
• Lattice fermion formulation via Physics-Informed Neural Networks: Ginsparg-Wilson relation and Overlap fermions