DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning estimators for lattice QCD observables

Abstract

A novel technique using machine learning (ML) to reduce the computational cost of evaluating lattice 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 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 CP violating interaction, the quark chromoelectric dipole moment interaction, is added to QCD, again from the two-point correlation functions calculated without CP violation.

Authors:
; ;
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1532580
Alternate Identifier(s):
OSTI ID: 1558963
Report Number(s):
LA-UR-18-26411
Journal ID: ISSN 2470-0010; PRVDAQ; 014504
Grant/Contract Number:  
AC02-05CH11231; AC05-00OR22725; 89233218CNA000001
Resource Type:
Published Article
Journal Name:
Physical Review D
Additional Journal Information:
Journal Name: Physical Review D Journal Volume: 100 Journal Issue: 1; Journal ID: ISSN 2470-0010
Publisher:
American Physical Society
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; Atomic, Nuclear and Particle Physics; Computer Science

Citation Formats

Yoon, Boram, Bhattacharya, Tanmoy, and Gupta, Rajan. Machine learning estimators for lattice QCD observables. United States: N. p., 2019. Web. doi:10.1103/PhysRevD.100.014504.
Yoon, Boram, Bhattacharya, Tanmoy, & Gupta, Rajan. Machine learning estimators for lattice QCD observables. United States. https://doi.org/10.1103/PhysRevD.100.014504
Yoon, Boram, Bhattacharya, Tanmoy, and Gupta, Rajan. Tue . "Machine learning estimators for lattice QCD observables". United States. https://doi.org/10.1103/PhysRevD.100.014504.
@article{osti_1532580,
title = {Machine learning estimators for lattice QCD observables},
author = {Yoon, Boram and Bhattacharya, Tanmoy and Gupta, Rajan},
abstractNote = {A novel technique using machine learning (ML) to reduce the computational cost of evaluating lattice 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 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 CP violating interaction, the quark chromoelectric dipole moment interaction, is added to QCD, again from the two-point correlation functions calculated without CP violation.},
doi = {10.1103/PhysRevD.100.014504},
journal = {Physical Review D},
number = 1,
volume = 100,
place = {United States},
year = {2019},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1103/PhysRevD.100.014504

Citation Metrics:
Cited by: 11 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Low-energy precision tests of supersymmetry
journal, January 2008


Effective noise reduction techniques for disconnected loops in Lattice QCD
journal, September 2010

  • Bali, Gunnar S.; Collins, Sara; Schäfer, Andreas
  • Computer Physics Communications, Vol. 181, Issue 9
  • DOI: 10.1016/j.cpc.2010.05.008

Monte Carlo study of quantized SU(2) gauge theory
journal, April 1980


Linear Inversion of Band-Limited Reflection Seismograms
journal, October 1986

  • Santosa, Fadil; Symes, William W.
  • SIAM Journal on Scientific and Statistical Computing, Vol. 7, Issue 4
  • DOI: 10.1137/0907087

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


Bootstrap Methods: Another Look at the Jackknife
journal, January 1979


Nucleon charges and electromagnetic form factors from 2 + 1 + 1 -flavor lattice QCD
journal, May 2014


New class of variance-reduction techniques using lattice symmetries
journal, November 2013


Axial, scalar, and tensor charges of the nucleon from 2 + 1 + 1 -flavor Lattice QCD
journal, September 2016


Confinement of quarks
journal, October 1974


Machine learning of explicit order parameters: From the Ising model to SU(2) lattice gauge theory
journal, November 2017


Adaptive Multigrid Algorithm for the Lattice Wilson-Dirac Operator
journal, November 2010


Machine learning action parameters in lattice quantum chromodynamics
journal, May 2018


Enhanced Higgs Boson to τ + τ Search with Deep Learning
journal, March 2015


Deep learning beyond Lefschetz thimbles
journal, November 2017


Stochastic gradient boosting
journal, February 2002


Electric dipole moments as probes of new physics
journal, July 2005


Neutron and proton electric dipole moments from N f = 2 + 1 domain-wall fermion lattice QCD
journal, May 2016


Probing novel scalar and tensor interactions from (ultra)cold neutrons to the LHC
journal, March 2012


Ridge Regression: Biased Estimation for Nonorthogonal Problems
journal, February 1970


Dimension-5 C P -odd operators: QCD mixing and renormalization
journal, December 2015


Searching for exotic particles in high-energy physics with deep learning
journal, July 2014

  • Baldi, P.; Sadowski, P.; Whiteson, D.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms5308

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


Controlling excited-state contamination in nucleon matrix elements
journal, June 2016


Electric dipole moments of nucleons, nuclei, and atoms: The Standard Model and beyond
journal, July 2013

  • Engel, Jonathan; Ramsey-Musolf, Michael J.; van Kolck, U.
  • Progress in Particle and Nuclear Physics, Vol. 71
  • DOI: 10.1016/j.ppnp.2013.03.003

machine.
journal, October 2001


Towards a determination of the nucleon EDM from the quark chromo-EDM operator with the gradient flow
conference, May 2019

  • Kim, Jangho; Dragos, Jack; Shindler, Andrea
  • Proceedings of The 36th Annual International Symposium on Lattice Field Theory — PoS(LATTICE2018)
  • DOI: 10.22323/1.334.0260

Isovector charges of the nucleon from 2 + 1 + 1 -flavor lattice QCD
journal, August 2018


Neutron Electric Dipole Moment and Tensor Charges from Lattice QCD
journal, November 2015


Neutron Electric Dipole Moment from Beyond the Standard Model
conference, May 2019

  • Bhattacharya, Tanmoy; Yoon, Boram; Gupta, Rajan
  • Proceedings of The 36th Annual International Symposium on Lattice Field Theory — PoS(LATTICE2018)
  • DOI: 10.22323/1.334.0188

The Chroma Software System for Lattice QCD
journal, March 2005


Regression Shrinkage and Selection Via the Lasso
journal, January 1996


Works referencing / citing this record:

Status and future perspectives for lattice gauge theory calculations to the exascale and beyond
journal, November 2019

  • Joó, Bálint; Jung, Chulwoo; Christ, Norman H.
  • The European Physical Journal A, Vol. 55, Issue 11
  • DOI: 10.1140/epja/i2019-12919-7