Gauge covariant neural network for quarks and gluons
arXiv:2103.11965 · doi:10.1103/PhysRevD.111.074501
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.
arXiv comment18 pages, 6 figures
References in corpus (28)
- Properties and uses of the Wilson flow in lattice QCD
- FLAG Review 2019
- Analytic Smearing of SU(3) Link Variables in Lattice QCD
- Highly Improved Staggered Quarks on the Lattice, with Applications to Charm Physics
- Trivializing maps, the Wilson flow and the HMC algorithm
- Variants of fattening and flavor symmetry restoration
- Flow-based generative models for Markov chain Monte Carlo in lattice field theory
- Chiral symmetry and the Yang--Mills gradient flow
- Equivariant flow-based sampling for lattice gauge theory
- Scaling studies of QCD with the dynamical HISQ action
- Hypercubic Smeared Links for Dynamical Fermions
- Sampling using gauge equivariant flows
- Regressive and generative neural networks for scalar field theory
- Evidence of effective axial U(1) symmetry restoration at high temperature QCD
- Rationale for UV-filtered clover fermions
- Lattice gauge equivariant convolutional neural networks
- Flow-based sampling for fermionic lattice field theories
- Hybrid Monte Carlo with Fat Link Fermion Actions
- Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions
- Self-learning Hybrid Monte Carlo: A First-principles Approach
- Flow-based sampling in the lattice Schwinger model at criticality
- Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
- Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
- Learning Trivializing Gradient Flows for Lattice Gauge Theories
- Numerical determination of the width and shape of the effective string using Stochastic Normalizing Flows
- Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
- Neural-network preconditioners for solving the Dirac equation in lattice gauge theory
- Temperature dependence and limiting mechanisms of the upper critical field of FeSe thin films