2018/01/17 by Phiala E. Shanahan, Amalie Trewartha, Daniel Trewartha +1
Mathematics · Physics and Astronomy · #Artificial intelligence #Artificial neural network #Computer science #High-Energy Particle Collisions Research #Homogeneous space #Lattice (music) #Lattice QCD #Lattice gauge theory #Machine learning #Mathematics #Parametric statistics #Particle physics #Particle physics theoretical and experimental studies #Physics #Principal component analysis #Quantum Chromodynamics and Particle Interactions #Quantum chromodynamics #Statistical physics #Statistics #cond-mat.dis-nn #hep-lat
paper · pdf · doi:10.1103/physrevd.97.094506
published as Phys. Rev. D 97, 094506 (2018)
arxiv created 2018/01/17 · openalex publication_date 2018/05/16 · arxiv updated 2021/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Numerical lattice quantum chromodynamics studies of the strong interaction are important in many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. The high information content and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.