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

Title: Machine learning action parameters in lattice quantum chromodynamics

Abstract

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.

Authors:
; ;
Publication Date:
Research Org.:
Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA); National Science Foundation (NSF)
OSTI Identifier:
1437340
Alternate Identifier(s):
OSTI ID: 1438377; OSTI ID: 1635166
Report Number(s):
JLAB-THY-18-2627; DOE/OR/23177-4325; arXiv:1801.05784; MIT-CTP/4980
Journal ID: ISSN 2470-0010; PRVDAQ; 094506
Grant/Contract Number:  
SC0010495; SC0011090; SC0018121; AC05-06OR23177; 0922770
Resource Type:
Published Article
Journal Name:
Physical Review. D.
Additional Journal Information:
Journal Name: Physical Review. D. Journal Volume: 97 Journal Issue: 9; Journal ID: ISSN 2470-0010
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
73 NUCLEAR PHYSICS AND RADIATION PHYSICS

Citation Formats

Shanahan, Phiala E., Trewartha, Daniel, and Detmold, William. Machine learning action parameters in lattice quantum chromodynamics. United States: N. p., 2018. Web. doi:10.1103/PhysRevD.97.094506.
Shanahan, Phiala E., Trewartha, Daniel, & Detmold, William. Machine learning action parameters in lattice quantum chromodynamics. United States. https://doi.org/10.1103/PhysRevD.97.094506
Shanahan, Phiala E., Trewartha, Daniel, and Detmold, William. Wed . "Machine learning action parameters in lattice quantum chromodynamics". United States. https://doi.org/10.1103/PhysRevD.97.094506.
@article{osti_1437340,
title = {Machine learning action parameters in lattice quantum chromodynamics},
author = {Shanahan, Phiala E. and Trewartha, Daniel and Detmold, William},
abstractNote = {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.},
doi = {10.1103/PhysRevD.97.094506},
journal = {Physical Review. D.},
number = 9,
volume = 97,
place = {United States},
year = {Wed May 16 00:00:00 EDT 2018},
month = {Wed May 16 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1103/PhysRevD.97.094506

Citation Metrics:
Cited by: 39 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Multigrid Monte Carlo Method for Lattice Field Theories
journal, March 1986


Hybrid Monte Carlo
journal, September 1987


Multigrid Monte Carlo algorithms for SU(2) lattice gauge theory: Two versus four dimensions
journal, December 1994


Light asymmetric dark matter on the lattice: SU(2) technicolor with two fundamental flavors
journal, January 2012


Lattice QCD input for nuclear structure and reactions
journal, January 2018


Applications of neural networks to the studies of phase transitions of two-dimensional Potts models
journal, April 2018


Critical slowing down and error analysis in lattice QCD simulations
journal, April 2011


LIII. On lines and planes of closest fit to systems of points in space
journal, November 1901

  • Pearson, Karl
  • The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, Vol. 2, Issue 11
  • DOI: 10.1080/14786440109462720

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


Machine Learning Phases of Strongly Correlated Fermions
journal, August 2017


Finite-lattice approximations to renormalization groups
journal, May 1975


Discovering phase transitions with unsupervised learning
journal, November 2016


The pivot algorithm: A highly efficient Monte Carlo method for the self-avoiding walk
journal, January 1988

  • Madras, Neal; Sokal, Alan D.
  • Journal of Statistical Physics, Vol. 50, Issue 1-2
  • DOI: 10.1007/BF01022990

Multiscale Monte Carlo equilibration: Two-color QCD with two fermion flavors
journal, December 2016


I = 2 π π scattering from fully-dynamical mixed-action lattice QCD
journal, March 2006


Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
journal, June 2000

  • Hahnloser, Richard H. R.; Sarpeshkar, Rahul; Mahowald, Misha A.
  • Nature, Vol. 405, Issue 6789
  • DOI: 10.1038/35016072

Finding Minimum Entropy Codes
journal, September 1989


Measurement of the π p elastic scattering cross section near 180° between 600 and 1280 MeV/ c
journal, July 1974


A new Directed Divergence Measure and its Characterization∗
journal, May 1990


The dropout learning algorithm
journal, May 2014


The Contiguity Ratio and Statistical Mapping
journal, November 1954

  • Geary, R. C.
  • The Incorporated Statistician, Vol. 5, Issue 3
  • DOI: 10.2307/2986645

Block renormalization group for Euclidean Fermions
journal, June 1989

  • Balaban, Tadeusz; O'Carroll, Michael; Schor, Ricardo
  • Communications in Mathematical Physics, Vol. 122, Issue 2
  • DOI: 10.1007/BF01257414

Solving the quantum many-body problem with artificial neural networks
journal, February 2017


Machine learning phases of matter
journal, February 2017

  • Carrasquilla, Juan; Melko, Roger G.
  • Nature Physics, Vol. 13, Issue 5
  • DOI: 10.1038/nphys4035

Notes on Continuous Stochastic Phenomena
journal, January 1950


Exploring cluster Monte Carlo updates with Boltzmann machines
journal, November 2017


Self-learning Monte Carlo method
journal, January 2017


Nuclear physics from lattice QCD
journal, January 2011

  • Beane, S. R.; Detmold, W.; Orginos, K.
  • Progress in Particle and Nuclear Physics, Vol. 66, Issue 1
  • DOI: 10.1016/j.ppnp.2010.08.002

Multi-grid Monte Carlo (II). Two-dimensional XY model
journal, May 1991


A new class of metric divergences on probability spaces and its applicability in statistics
journal, September 2003

  • Österreicher, Ferdinand; Vajda, Igor
  • Annals of the Institute of Statistical Mathematics, Vol. 55, Issue 3
  • DOI: 10.1007/BF02517812

Accelerated Monte Carlo simulations with restricted Boltzmann machines
journal, January 2017


Self-organization in a perceptual network
journal, March 1988


Machine Learning Topological Invariants with Neural Networks
journal, February 2018


Dark nuclei. II. Nuclear spectroscopy in two-color QCD
journal, December 2014


Multi-grid Monte Carlo (III). Two-dimensional O(4)-symmetric non-linear σ-model
journal, August 1992


Moments of nucleon spin-dependent generalized parton distributions
journal, March 2004


Multiscale Monte Carlo equilibration: Pure Yang-Mills theory
journal, December 2015


Confinement of quarks
journal, October 1974


Quantum Chromodynamics on the Lattice
book, January 2010


Review of lattice results concerning low-energy particle physics: Flavour Lattice Averaging Group (FLAG)
journal, February 2017


Fixed point actions for Wilson fermions
journal, October 1993


On Information and Sufficiency
journal, March 1951

  • Kullback, S.; Leibler, R. A.
  • The Annals of Mathematical Statistics, Vol. 22, Issue 1
  • DOI: 10.1214/aoms/1177729694

Perfect Actions: From the Theoretical Background to Recent Developments
journal, January 1998


Relations Between two sets of Variates
journal, December 1936


Learning thermodynamics with Boltzmann machines
journal, October 2016


Thermodynamics of strong-interaction matter from lattice QCD
journal, October 2015

  • Ding, Heng-Tong; Karsch, Frithjof; Mukherjee, Swagato
  • International Journal of Modern Physics E, Vol. 24, Issue 10
  • DOI: 10.1142/S0218301315300076

A new metric for probability distributions
journal, July 2003

  • Endres, D. M.; Schindelin, J. E.
  • IEEE Transactions on Information Theory, Vol. 49, Issue 7
  • DOI: 10.1109/TIT.2003.813506

Perfect lattice action for asymptotically free theories
journal, February 1994


Representations of the rotation reflection symmetry group of the four-dimensional cubic lattice
journal, November 1983


Divergence measures based on the Shannon entropy
journal, January 1991

  • Lin, J.
  • IEEE Transactions on Information Theory, Vol. 37, Issue 1
  • DOI: 10.1109/18.61115

Erratum: Properties and uses of the Wilson flow in lattice QCD
journal, March 2014


Lattice QCD with mixed actions
journal, August 2005


Properties and uses of the Wilson flow in lattice QCD
journal, August 2010


Analysis of a complex of statistical variables into principal components.
journal, January 1933

  • Hotelling, H.
  • Journal of Educational Psychology, Vol. 24, Issue 6
  • DOI: 10.1037/h0071325

The renormalization group and the ε expansion
journal, August 1974


The Chroma Software System for Lattice QCD
journal, March 2005