Machine Learning Estimators for Lattice QCD Observables

Abstract

A novel technique using machine learning (ML) to reduce the computational cost of evaluating lattice quantum chromodynamics (QCD) observables is presented. The ML is trained on a subset of background gauge field configurations, called the labeled set, to predict an observable $O$ from the values of correlated, but less compute-intensive, observables $\mathbf{X}$ calculated on the full sample. By using a second subset, also part of the labeled set, we estimate the bias in the result predicted by the trained ML algorithm. A reduction in the computational cost by about $7\%-38\%$ is demonstrated for two different lattice QCD calculations using the Boosted decision tree regression ML algorithm: (1) prediction of the nucleon three-point correlation functions that yield isovector charges from the two-point correlation functions, and (2) prediction of the phase acquired by the neutron mass when a small Charge-Parity (CP) violating interaction, the quark chromoelectric dipole moment interaction, is added to QCD, again from the two-point correlation functions calculated without CP violation.

8 pages, 5 figures

References in corpus (8)

• Highly Improved Staggered Quarks on the Lattice, with Applications to Charm Physics
• Adaptive multigrid algorithm for the lattice Wilson-Dirac operator
• Isovector Charges of the Nucleon from 2+1+1-flavor Lattice QCD
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Low Energy Precision Test of Supersymmetry
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Deep Learning Beyond Lefschetz Thimbles
• Machine learning action parameters in lattice quantum chromodynamics

Cited by in corpus (17)

• Machine Learning in Nuclear Physics
• Nuclear matrix elements from lattice QCD for electroweak and beyond-Standard-Model processes
• Stochastic normalizing flows as non-equilibrium transformations
• Status and Future Perspectives for Lattice Gauge Theory Calculations to the Exascale and Beyond
• 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
• Machine-Learning Prediction for Quasi-PDF Matrix Elements
• A Neural Networks study of the phase transitions of Potts model
• Machine learning phases and criticalities without using real data for training
• Machine learning spectral functions in lattice QCD
• A machine learning approach for efficient multi-dimensional integration
• Lossy compression of statistical data using quantum annealer
• A regression algorithm for accelerated lattice QCD that exploits sparse inference on the D-Wave quantum annealer
• Equivariance and generalization in neural networks
• Constructing and Machine Learning Calabi-Yau Five-folds
• Predicting the Masses of Exotic Hadrons with Data Augmentation Using Multilayer Perceptron
• Nuclear correlation functions using first-principle calculations of lattice quantum chromodynamics