Litcius/Paper detail

Learning trivializing gradient flows for lattice gauge theories

Simone Bacchio, Pan Kessel, Stefan Schaefer, Lorenz Vaitl

2023Physical review. D/Physical review. D.32 citationsDOIOpen Access PDF

Abstract

We propose a unifying approach that starts from the perturbative construction of trivializing maps by L\"uscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of lattice field theory and requires several orders of magnitude fewer parameters than any existing machine learning approach. Specifically, our model can achieve competitive performance with as few as 14 parameters while existing deep-learning models have around 1 million parameters for $SU(3)$ Yang-Mills theory on a ${16}^{2}$ lattice. This has obvious consequences for training speed and interpretability. It also provides a plausible path for scaling machine-learning approaches toward realistic theories.

Topics & Concepts

InterpretabilityComputer scienceLattice (music)ScalingBalanced flowGauge theoryLattice gauge theoryArtificial intelligenceLattice field theoryStatistical physicsPhysicsMathematicsQuantum mechanicsGeometryMathematical analysisAcousticsTheoretical and Computational PhysicsQuantum Chromodynamics and Particle InteractionsParticle physics theoretical and experimental studies