skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine-learning prediction for quasiparton distribution function matrix elements

Abstract

There have been rapid developments in the direct calculation in lattice QCD (LQCD) of the Bjorken-x dependence of hadron structure through large-momentum effective theory (LaMET). LaMET overcomes the previous limitation of LQCD to moments (that is, integrals over Bjorken x) of hadron structure, allowing LQCD to directly provide the kinematic regions where the experimental values are least known. LaMET requires large-momentum hadron states to minimize its systematics and allow us to reach small- x reliably. This means that very fine lattice spacing to minimize lattice artifacts at order $$(P_za)^n$$ will become crucial for next-generation LaMET-like structure calculations. Furthermore, such calculations require operators with long Wilson-link displacements, especially in finer lattice units, increasing the communication costs relative to that of the propagator inversion. In this work, we explore whether machine-learning algorithms can make predictions of correlators to reduce the computational cost of these LQCD calculations. We consider two algorithms, gradient-boosting decision tree and linear models, applied to LaMET data, the matrix elements needed to determine the kaon and $$η_s$$ unpolarized parton distribution functions (PDFs), meson distribution amplitude (DA), and the nucleon gluon PDF. We find that both algorithms can reliably predict the target observables with different prediction accuracy and systematic errors. The predictions from smaller displacement z to larger ones work better than those for momentum p due to the higher correlation among the data.

Authors:
ORCiD logo; ORCiD logo; ; ;
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
Sponsoring Org.:
USDOE Office of Science (SC), Nuclear Physics (NP); National Science Foundation (NSF); USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR). Scientific Discovery through Advanced Computing (SciDAC); USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1601715
Alternate Identifier(s):
OSTI ID: 1760568
Report Number(s):
LA-UR-19-30235; MSUHEP-19-021
Journal ID: ISSN 2470-0010; PRVDAQ; 034516
Grant/Contract Number:  
89233218CNA000001; AC02-05CH11231; PHY 1653405
Resource Type:
Published Article
Journal Name:
Physical Review D
Additional Journal Information:
Journal Name: Physical Review D Journal Volume: 101 Journal Issue: 3; Journal ID: ISSN 2470-0010
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Zhang, Rui, Fan, Zhouyou, Li, Ruizi, Lin, Huey-Wen, and Yoon, Boram. Machine-learning prediction for quasiparton distribution function matrix elements. United States: N. p., 2020. Web. doi:10.1103/PhysRevD.101.034516.
Zhang, Rui, Fan, Zhouyou, Li, Ruizi, Lin, Huey-Wen, & Yoon, Boram. Machine-learning prediction for quasiparton distribution function matrix elements. United States. doi:https://doi.org/10.1103/PhysRevD.101.034516
Zhang, Rui, Fan, Zhouyou, Li, Ruizi, Lin, Huey-Wen, and Yoon, Boram. Mon . "Machine-learning prediction for quasiparton distribution function matrix elements". United States. doi:https://doi.org/10.1103/PhysRevD.101.034516.
@article{osti_1601715,
title = {Machine-learning prediction for quasiparton distribution function matrix elements},
author = {Zhang, Rui and Fan, Zhouyou and Li, Ruizi and Lin, Huey-Wen and Yoon, Boram},
abstractNote = {There have been rapid developments in the direct calculation in lattice QCD (LQCD) of the Bjorken-x dependence of hadron structure through large-momentum effective theory (LaMET). LaMET overcomes the previous limitation of LQCD to moments (that is, integrals over Bjorken x) of hadron structure, allowing LQCD to directly provide the kinematic regions where the experimental values are least known. LaMET requires large-momentum hadron states to minimize its systematics and allow us to reach small- x reliably. This means that very fine lattice spacing to minimize lattice artifacts at order $(P_za)^n$ will become crucial for next-generation LaMET-like structure calculations. Furthermore, such calculations require operators with long Wilson-link displacements, especially in finer lattice units, increasing the communication costs relative to that of the propagator inversion. In this work, we explore whether machine-learning algorithms can make predictions of correlators to reduce the computational cost of these LQCD calculations. We consider two algorithms, gradient-boosting decision tree and linear models, applied to LaMET data, the matrix elements needed to determine the kaon and $η_s$ unpolarized parton distribution functions (PDFs), meson distribution amplitude (DA), and the nucleon gluon PDF. We find that both algorithms can reliably predict the target observables with different prediction accuracy and systematic errors. The predictions from smaller displacement z to larger ones work better than those for momentum p due to the higher correlation among the data.},
doi = {10.1103/PhysRevD.101.034516},
journal = {Physical Review D},
number = 3,
volume = 101,
place = {United States},
year = {2020},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: https://doi.org/10.1103/PhysRevD.101.034516

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Lattice calculation of parton distributions
journal, July 2015


Improved parton distribution functions at the physical pion mass
journal, September 2018


Gaussian-weighted parton quasi-distribution (Lattice Parton Physics Project (LP3))
journal, April 2019

  • Ishikawa, Tomomi; Jin, LuChang; Lin, Huey-Wen
  • Science China Physics, Mechanics & Astronomy, Vol. 62, Issue 9
  • DOI: 10.1007/s11433-018-9375-1

Hadrons and nuclei
journal, November 2019

  • Detmold, William; Edwards, Robert G.; Dudek, Jozef J.
  • The European Physical Journal A, Vol. 55, Issue 11
  • DOI: 10.1140/epja/i2019-12902-4

Parton distributions and lattice QCD calculations: A community white paper
journal, May 2018

  • Lin, Huey-Wen; Nocera, Emanuele R.; Olness, Fred
  • Progress in Particle and Nuclear Physics, Vol. 100
  • DOI: 10.1016/j.ppnp.2018.01.007

Lattice QCD ensembles with four flavors of highly improved staggered quarks
journal, March 2013


Novel quark smearing for hadrons with high momenta in lattice QCD
journal, May 2016


Nonperturbative Renormalization of Nonlocal Quark Bilinears for Parton Quasidistribution Functions on the Lattice Using an Auxiliary Field
journal, July 2018


Physics of the Gluon-Helicity Contribution to Proton Spin
journal, September 2013


Justifying the naive partonic sum rule for proton spin
journal, April 2015


Lattice QCD exploration of parton pseudo-distribution functions
journal, November 2017


Flavor symmetry and the static potential with hypercubic blocking
journal, July 2001


Kaon distribution amplitude from lattice QCD and the flavor SU(3) symmetry
journal, February 2019


Gradient boosting machines, a tutorial
journal, January 2013


First direct lattice-QCD calculation of the x -dependence of the pion parton distribution function
journal, August 2019


Stochastic gradient boosting
journal, February 2002


Parton physics from large-momentum effective field theory
journal, May 2014


Perturbative renormalization of quasi-parton distribution functions
journal, September 2017


Parton distribution function with nonperturbative renormalization from lattice QCD
journal, January 2018


Parton distribution functions from Ioffe time pseudo-distributions
journal, December 2019

  • Joó, Bálint; Karpie, Joseph; Orginos, Kostas
  • Journal of High Energy Physics, Vol. 2019, Issue 12
  • DOI: 10.1007/JHEP12(2019)081

Lattice finite-volume dependence of the nucleon parton distributions
journal, October 2019


A complete non-perturbative renormalization prescription for quasi-PDFs
journal, October 2017


One-loop matching for generalized parton distributions
journal, July 2015


Quasi-parton distribution functions, momentum distributions, and pseudo-parton distribution functions
journal, August 2017


Machine learning estimators for lattice QCD observables
journal, July 2019


QCD Factorization for B π π Decays: Strong Phases and CP Violation in the Heavy Quark Limit
journal, September 1999


Parton Physics on a Euclidean Lattice
journal, June 2013


Gluon helicity Δ G from a universality class of operators on a lattice
journal, April 2014


Reconstructing parton distribution functions from Ioffe time data: from Bayesian methods to neural networks
journal, April 2019

  • Karpie, Joseph; Orginos, Kostas; Rothkopf, Alexander
  • Journal of High Energy Physics, Vol. 2019, Issue 4
  • DOI: 10.1007/JHEP04(2019)057

QCD factorization in B→πK, ππ decays and extraction of Wolfenstein parameters
journal, July 2001


Highly improved staggered quarks on the lattice with applications to charm physics
journal, March 2007


Gluon Quasi-Parton-Distribution Functions from Lattice QCD
journal, December 2018


Flavor structure of the nucleon sea from lattice QCD
journal, March 2015


Nucleon helicity and transversity parton distributions from lattice QCD
journal, October 2016


Domain wall QCD with physical quark masses
journal, April 2016


Pion distribution amplitude from lattice QCD
journal, May 2017


Pion valence structure from Ioffe-time parton pseudodistribution functions
journal, December 2019


machine.
journal, October 2001


Pion and kaon structure at the electron-ion collider
journal, October 2019

  • Aguilar, Arlene C.; Ahmed, Zafir; Aidala, Christine
  • The European Physical Journal A, Vol. 55, Issue 10
  • DOI: 10.1140/epja/i2019-12885-0

Symmetry properties of nonlocal quark bilinear operators on a Lattice (LP 3 Collaboration)
journal, September 2019


Updated lattice results for parton distributions
journal, July 2017

  • Alexandrou, Constantia; Cichy, Krzysztof; Constantinou, Martha
  • Physical Review D, Vol. 96, Issue 1
  • DOI: 10.1103/PhysRevD.96.014513

Parton distributions from lattice QCD
journal, August 2001


The Chroma Software System for Lattice QCD
journal, March 2005