Litcius/Paper detail

Learning lattice quantum field theories with equivariant continuous flows

Mathis Gerdes, Pim de Haan, Corrado Rainone, Roberto Bondesan, Miranda C. N. Cheng

2023SciPost Physics35 citationsDOIOpen Access PDF

Abstract

We propose a novel machine learning method for sampling from the high-dimensional probability distributions of Lattice Field Theories, which is based on a single neural ODE layer and incorporates the full symmetries of the problem. We test our model on the \phi^4 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:msup> <mml:mi>ϕ</mml:mi> <mml:mn>4</mml:mn> </mml:msup> </mml:math> theory, showing that it systematically outperforms previously proposed flow-based methods in sampling efficiency, and the improvement is especially pronounced for larger lattices. Furthermore, we demonstrate that our model can learn a continuous family of theories at once, and the results of learning can be transferred to larger lattices. Such generalizations further accentuate the advantages of machine learning methods.

Topics & Concepts

Equivariant mapOdeLattice (music)Homogeneous spaceComputer scienceArtificial intelligenceAlgorithmMachine learningMathematicsApplied mathematicsPure mathematicsPhysicsGeometryAcousticsTheoretical and Computational PhysicsQuantum many-body systemsPhysics of Superconductivity and Magnetism
Learning lattice quantum field theories with equivariant continuous flows | Litcius