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

Title: A perspective on machine learning and data science for strongly correlated electron problems

Abstract

Numerical approaches to the correlated electron problem have achieved considerable success, yet are still constrained by several bottlenecks, including high order polynomial or exponential scaling in system size, long autocorrelation times, challenges in recognizing novel phases, and the Fermion sign problem. Methods in machine learning (ML), artificial intelligence, and data science promise to help address these limitations and open up a new frontier in strongly correlated quantum system simulations. In this paper, we review some of the progress in this area. We begin by examining these approaches in the context of classical models, where their underpinnings and application can be easily illustrated and benchmarked. We then discuss cases where ML methods have enabled scientific discovery. Finally, we will examine their applications in accelerating model solutions in state-of-the-art quantum many-body methods like quantum Monte Carlo and discuss potential future research directions.

Authors:
ORCiD logo; ORCiD logo;
Publication Date:
Research Org.:
Univ. of Tennessee, Knoxville, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1897543
Alternate Identifier(s):
OSTI ID: 1907641
Grant/Contract Number:  
SC0022311
Resource Type:
Published Article
Journal Name:
Carbon Trends
Additional Journal Information:
Journal Name: Carbon Trends Journal Volume: 9 Journal Issue: C; Journal ID: ISSN 2667-0569
Publisher:
Elsevier
Country of Publication:
United Kingdom
Language:
English
Subject:
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; Many-body physics; Quantum materials; Machine learning

Citation Formats

Johnston, Steven, Khatami, Ehsan, and Scalettar, Richard. A perspective on machine learning and data science for strongly correlated electron problems. United Kingdom: N. p., 2022. Web. doi:10.1016/j.cartre.2022.100231.
Johnston, Steven, Khatami, Ehsan, & Scalettar, Richard. A perspective on machine learning and data science for strongly correlated electron problems. United Kingdom. https://doi.org/10.1016/j.cartre.2022.100231
Johnston, Steven, Khatami, Ehsan, and Scalettar, Richard. Sat . "A perspective on machine learning and data science for strongly correlated electron problems". United Kingdom. https://doi.org/10.1016/j.cartre.2022.100231.
@article{osti_1897543,
title = {A perspective on machine learning and data science for strongly correlated electron problems},
author = {Johnston, Steven and Khatami, Ehsan and Scalettar, Richard},
abstractNote = {Numerical approaches to the correlated electron problem have achieved considerable success, yet are still constrained by several bottlenecks, including high order polynomial or exponential scaling in system size, long autocorrelation times, challenges in recognizing novel phases, and the Fermion sign problem. Methods in machine learning (ML), artificial intelligence, and data science promise to help address these limitations and open up a new frontier in strongly correlated quantum system simulations. In this paper, we review some of the progress in this area. We begin by examining these approaches in the context of classical models, where their underpinnings and application can be easily illustrated and benchmarked. We then discuss cases where ML methods have enabled scientific discovery. Finally, we will examine their applications in accelerating model solutions in state-of-the-art quantum many-body methods like quantum Monte Carlo and discuss potential future research directions.},
doi = {10.1016/j.cartre.2022.100231},
journal = {Carbon Trends},
number = C,
volume = 9,
place = {United Kingdom},
year = {Sat Oct 01 00:00:00 EDT 2022},
month = {Sat Oct 01 00:00:00 EDT 2022}
}

Works referenced in this record:

New results on Trotter-like approximations
journal, May 1986


Exact SO(5) Symmetry in the Spin- 3 / 2 Fermionic System
journal, October 2003


Machine learning method for tight-binding Hamiltonian parameterization from ab-initio band structure
journal, January 2021


Equivalence of restricted Boltzmann machines and tensor network states
journal, February 2018


Maximally localized Wannier functions: Theory and applications
journal, October 2012

  • Marzari, Nicola; Mostofi, Arash A.; Yates, Jonathan R.
  • Reviews of Modern Physics, Vol. 84, Issue 4
  • DOI: 10.1103/RevModPhys.84.1419

Machine learning quantum phases of matter beyond the fermion sign problem
journal, August 2017


Two-dimensional negative- U Hubbard model
journal, February 1991


Light Bipolarons Stabilized by Peierls Electron-Phonon Coupling
journal, December 2018


The critical temperature of the 2D-Ising model through deep learning autoencoders
journal, December 2020

  • Alexandrou, Constantia; Athenodorou, Andreas; Chrysostomou, Charalambos
  • The European Physical Journal B, Vol. 93, Issue 12
  • DOI: 10.1140/epjb/e2020-100506-5

Langevin simulations of the half-filled cubic Holstein model
journal, October 2020


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


Numerical study of the two-dimensional Hubbard model
journal, July 1989


From BCS-like superconductivity to condensation of local pairs: A numerical study of the attractive Hubbard model
journal, July 1996


Machine learning vortices at the Kosterlitz-Thouless transition
journal, January 2018


Two-dimensional attractive Hubbard model and the BCS-BEC crossover
journal, May 2022

  • Fontenele, Rodrigo A.; Costa, Natanael C.; dos Santos, Raimundo R.
  • Physical Review B, Vol. 105, Issue 18
  • DOI: 10.1103/PhysRevB.105.184502

Orbital structure of the effective pairing interaction in the high-temperature superconducting cuprates
journal, March 2021


Quantum spin liquid emerging in two-dimensional correlated Dirac fermions
journal, April 2010


Self-learning quantum Monte Carlo method in interacting fermion systems
journal, July 2017


Effective Ruderman–Kittel–Kasuya–Yosida-like Interaction in Diluted Double-exchange Model: Self-learning Monte Carlo Approach
journal, March 2021

  • Kohshiro, Hidehiko; Nagai, Yuki
  • Journal of the Physical Society of Japan, Vol. 90, Issue 3
  • DOI: 10.7566/JPSJ.90.034711

Energetics of Domain Walls in the 2D t J Model
journal, October 1998


Interplay of Site and Bond Electron-Phonon Coupling in One Dimension
journal, November 2016


Theory of the First-Order Magnetic Phase Change in U O 2
journal, January 1966


Machine learning topological states
journal, November 2017


Relative importance of nonlinear electron-phonon coupling and vertex corrections in the Holstein model
journal, August 2020


Two-dimensional Hubbard model: Numerical simulation study
journal, April 1985


Insulator, metal, or superconductor: The criteria
journal, April 1993

  • Scalapino, Douglas J.; White, Steven R.; Zhang, Shoucheng
  • Physical Review B, Vol. 47, Issue 13
  • DOI: 10.1103/PhysRevB.47.7995

Smallest neural network to learn the Ising criticality
journal, August 2018


Magnetism and Charge Order in the Honeycomb Lattice
journal, March 2021


Solving the electronic structure problem with machine learning
journal, February 2019

  • Chandrasekaran, Anand; Kamal, Deepak; Batra, Rohit
  • npj Computational Materials, Vol. 5, Issue 1
  • DOI: 10.1038/s41524-019-0162-7

Ising‐Model Spin Correlations on the Triangular Lattice
journal, August 1964

  • Stephenson, John
  • Journal of Mathematical Physics, Vol. 5, Issue 8
  • DOI: 10.1063/1.1704202

Machine learning sparse tight-binding parameters for defects
journal, May 2022

  • Schattauer, Christoph; Todorović, Milica; Ghosh, Kunal
  • npj Computational Materials, Vol. 8, Issue 1
  • DOI: 10.1038/s41524-022-00791-x

Detection of Phase Transition via Convolutional Neural Networks
journal, June 2017

  • Tanaka, Akinori; Tomiya, Akio
  • Journal of the Physical Society of Japan, Vol. 86, Issue 6
  • DOI: 10.7566/JPSJ.86.063001

Deriving models for the Kitaev spin-liquid candidate material α RuCl 3 from first principles
journal, August 2019


Bond excitations in the pseudogap phase of the Hubbard model
journal, December 2008


Superconductivity and charge density wave order in the two-dimensional Holstein model
journal, June 2021


Introduction to quantum Monte Carlo simulations for fermionic systems
journal, January 2003


Stripe order in the underdoped region of the two-dimensional Hubbard model
journal, November 2017


Competition of pairing and Peierls charge-density-wave correlations in a two-dimensional electron-phonon model
journal, July 1989

  • Scalettar, R. T.; Bickers, N. E.; Scalapino, D. J.
  • Physical Review B, Vol. 40, Issue 1
  • DOI: 10.1103/PhysRevB.40.197

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


Extraction of interaction parameters for αRuCl3 from neutron data using machine learning
journal, June 2022


Monte Carlo sampling methods using Markov chains and their applications
journal, April 1970


Density Matrix Renormalization Group Study of the Striped Phase in the 2D t J Model
journal, February 1998


Strong Coupling Superconductivity, Pseudogap, and Mott Transition
journal, May 2012


Neural Decoder for Topological Codes
journal, July 2017


Easing the Monte Carlo sign problem
journal, August 2020

  • Hangleiter, Dominik; Roth, Ingo; Nagaj, Daniel
  • Science Advances, Vol. 6, Issue 33
  • DOI: 10.1126/sciadv.abb8341

Plaquette versus ordinary d -wave pairing in the t -Hubbard model on a width-4 cylinder
journal, July 2020


Discrete Hubbard-Stratonovich transformation for fermion lattice models
journal, October 1983


Sign-Problem-Free Quantum Monte Carlo of the Onset of Antiferromagnetism in Metals
journal, December 2012


Machine learning in electronic-quantum-matter imaging experiments
journal, June 2019


Self-learning Monte Carlo method
journal, January 2017


Interplay of charge, spin, and lattice degrees of freedom in the spectral properties of the one-dimensional Hubbard-Holstein model
journal, November 2014


Physics-informed machine learning
journal, May 2021


Sign-Problem-Free Fermionic Quantum Monte Carlo: Developments and Applications
journal, March 2019


Monte Carlo tests of renormalization-group predictions for critical phenomena in Ising models
journal, April 2001


Quantum critical points and the sign problem
journal, January 2022


Dynamical mean field theory of polarons and bipolarons in the half-filled Holstein model
journal, July 2006


Sufficient condition for absence of the sign problem in the fermionic quantum Monte Carlo algorithm
journal, April 2005


Computational Complexity and Fundamental Limitations to Fermionic Quantum Monte Carlo Simulations
journal, May 2005


Scaling theory of Ising spin glasses
journal, June 1984


Classical spin dynamics based on SU(N) coherent states
journal, September 2021


Machine learning the Hubbard U parameter in DFT+U using Bayesian optimization
journal, November 2020


Superconductivity, charge density waves, and bipolarons in the Holstein model
journal, June 2021


Intertwined spin, charge, and pair correlations in the two-dimensional Hubbard model in the thermodynamic limit
journal, February 2022

  • Mai, Peizhi; Karakuzu, Seher; Balduzzi, Giovanni
  • Proceedings of the National Academy of Sciences, Vol. 119, Issue 7
  • DOI: 10.1073/pnas.2112806119

Machine-learning-assisted insight into spin ice Dy2Ti2O7
journal, February 2020


Efficient Dynamical Mean Field Simulation of the Holstein-Hubbard Model
journal, October 2007


Unsupervised machine learning account of magnetic transitions in the Hubbard model
journal, January 2018


Hubbard model on the honeycomb lattice: From static and dynamical mean-field theories to lattice quantum Monte Carlo simulations
journal, March 2020


Symmetry-enforced self-learning Monte Carlo method applied to the Holstein model
journal, July 2018


Extended Dynamical Mean Field Theory Study of the Periodic Anderson Model
journal, July 2003


Machine learning on neutron and x-ray scattering and spectroscopies
journal, September 2021

  • Chen, Zhantao; Andrejevic, Nina; Drucker, Nathan C.
  • Chemical Physics Reviews, Vol. 2, Issue 3
  • DOI: 10.1063/5.0049111

Geometric integration of classical spin dynamics via a mean-field Schrödinger equation
journal, August 2022


Robustness of antiferromagnetism in the Su-Schrieffer-Heeger Hubbard model
journal, August 2022


Competition between Antiferromagnetic Order and Spin-Liquid Behavior in the Two-Dimensional Periodic Anderson Model at Half Filling
journal, March 1995


Quantum Monte Carlo study of lattice polarons in the two-dimensional three-orbital Su–Schrieffer–Heeger model
journal, June 2020


Collective Monte Carlo Updating for Spin Systems
journal, January 1989


Majorana-Time-Reversal Symmetries: A Fundamental Principle for Sign-Problem-Free Quantum Monte Carlo Simulations
journal, December 2016


Ergodicity at large couplings with the determinant Monte Carlo algorithm
journal, November 1991

  • Scalettar, Richard T.; Noack, Reinhard M.; Singh, Rajiv R. P.
  • Physical Review B, Vol. 44, Issue 19
  • DOI: 10.1103/PhysRevB.44.10502

Meron-Cluster Solution of Fermion Sign Problems
journal, October 1999


Determinant quantum Monte Carlo study of the two-dimensional single-band Hubbard-Holstein model
journal, June 2013


Machine learning of frustrated classical spin models (II): Kernel principal component analysis
journal, June 2018


Ground-state and finite-temperature signatures of quantum phase transitions in the half-filled Hubbard model on a honeycomb lattice
journal, August 2005


Solutions to sign problems in lattice Yukawa models
journal, July 2012


Systematic Study of d -Wave Superconductivity in the 2D Repulsive Hubbard Model
journal, November 2005


Anomalously strong near-neighbor attraction in doped 1D cuprate chains
journal, September 2021


Ground-state phase diagram of the t-t-J model
journal, October 2021

  • Jiang, Shengtao; Scalapino, Douglas J.; White, Steven R.
  • Proceedings of the National Academy of Sciences, Vol. 118, Issue 44
  • DOI: 10.1073/pnas.2109978118

Metallicity in the half-filled Holstein-Hubbard model
journal, November 2008


Pairing fluctuations and pseudogaps in the attractive Hubbard model
journal, July 2001


Classifying snapshots of the doped Hubbard model with machine learning
journal, July 2019


Lattice field theory as a percolation process
journal, April 1988


Self-learning Monte Carlo method: Continuous-time algorithm
journal, October 2017


Sign problem in the numerical simulation of many-electron systems
journal, May 1990


Strange metallicity in the doped Hubbard model
journal, November 2019


Accelerating lattice quantum Monte Carlo simulations using artificial neural networks: Application to the Holstein model
journal, July 2019


Quantum magnetic properties of the S U ( 2 N ) Hubbard model in the square lattice: A quantum Monte Carlo study
journal, September 2013


Three-band Hubbard model: A Monte Carlo study
journal, May 1990


Finite-size effects in Luther-Emery phases of Holstein and Hubbard models
journal, December 2015


Studies of polaron motion
journal, November 1959


Quantum cluster theories
journal, October 2005


Periodic Anderson model in infinite dimensions
journal, March 1993


Phase diagram of the Hubbard model: Beyond the dynamical mean field
journal, November 2001


Solvable Model of a Spin-Glass
journal, December 1975


Quantum Entanglement in Deep Learning Architectures
journal, February 2019


Machine learning of frustrated classical spin models. I. Principal component analysis
journal, October 2017


Recommender engine for continuous-time quantum Monte Carlo methods
journal, March 2017


Discovering phase transitions with unsupervised learning
journal, November 2016


Identifying topological order through unsupervised machine learning
journal, May 2019


Learning Efficient, Collective Monte Carlo Moves with Variational Autoencoders
journal, May 2022

  • Monroe, Jacob I.; Shen, Vincent K.
  • Journal of Chemical Theory and Computation, Vol. 18, Issue 6
  • DOI: 10.1021/acs.jctc.2c00110

Visualizing strange metallic correlations in the two-dimensional Fermi-Hubbard model with artificial intelligence
journal, September 2020


Nonuniversal critical dynamics in Monte Carlo simulations
journal, January 1987


Sharp Transition for Single Polarons in the One-Dimensional Su-Schrieffer-Heeger Model
journal, December 2010


Monte Carlo Simulation in Statistical Physics
journal, January 1993

  • Binder, K.; Heermann, D.; Roelofs, Lyle
  • Computers in Physics, Vol. 7, Issue 2
  • DOI: 10.1063/1.4823159

Monte Carlo calculations of coupled boson-fermion systems. I
journal, October 1981


Critical temperature for the two-dimensional attractive Hubbard model
journal, May 2004


Itinerant quantum critical point with frustration and a non-Fermi liquid
journal, July 2018


Mitigating the Sign Problem through Basis Rotations
journal, May 2021


Split Orthogonal Group: A Guiding Principle for Sign-Problem-Free Fermionic Simulations
journal, December 2015


Learning phase transitions by confusion
journal, February 2017

  • van Nieuwenburg, Evert P. L.; Liu, Ye-Hua; Huber, Sebastian D.
  • Nature Physics, Vol. 13, Issue 5
  • DOI: 10.1038/nphys4037

Absence of a Spin Liquid Phase in the Hubbard Model on the Honeycomb Lattice
journal, December 2012

  • Sorella, Sandro; Otsuka, Yuichi; Yunoki, Seiji
  • Scientific Reports, Vol. 2, Issue 1
  • DOI: 10.1038/srep00992

Competition among various charge-inhomogeneous states and d -wave superconducting state in Hubbard models on square lattices
journal, January 2018


Fermion bag approach to lattice field theories
journal, July 2010


Solution to sign problems in half-filled spin-polarized electronic systems
journal, March 2014


Machine learning phases of matter
journal, February 2017

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

Self-learning Monte Carlo with deep neural networks
journal, May 2018


On the product of semi-groups of operators
journal, April 1959


Quantum Monte Carlo and exact diagonalization study of a dynamic Hubbard model
journal, May 2002


Generalization of the Fortuin-Kasteleyn-Swendsen-Wang representation and Monte Carlo algorithm
journal, September 1988


Principal component analysis for fermionic critical points
journal, November 2017


Solving the fermion sign problem in quantum Monte Carlo simulations by Majorana representation
journal, June 2015


Stripe order from the perspective of the Hubbard model
journal, April 2018

  • Huang, Edwin W.; Mendl, Christian B.; Jiang, Hong-Chen
  • npj Quantum Materials, Vol. 3, Issue 1
  • DOI: 10.1038/s41535-018-0097-0

Zero-temperature phases of the two-dimensional Hubbard-Holstein model: A non-Gaussian exact diagonalization study
journal, November 2020


Particle-hole asymmetry in the dynamical spin and charge responses of corner-shared 1D cuprates
journal, September 2021


Breakdown of the Migdal-Eliashberg theory: A determinant quantum Monte Carlo study
journal, April 2018


Stripes on a 6-Leg Hubbard Ladder
journal, September 2003


Alleviating the sign problem in quantum Monte Carlo simulations of spin-orbit-coupled multiorbital Hubbard models
journal, January 2020


Semi-Metal-Insulator Transition of the Hubbard Model in the Honeycomb Lattice
journal, August 1992


Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition
journal, February 1944


Observation of spatial charge and spin correlations in the 2D Fermi-Hubbard model
journal, September 2016


Spin density waves in the Hubbard model: A DMFT approach
journal, April 2014


Sign problem in Monte Carlo simulations of frustrated quantum spin systems
journal, July 2000


Bad metallic transport in a cold atom Fermi-Hubbard system
journal, December 2018

  • Brown, Peter T.; Mitra, Debayan; Guardado-Sanchez, Elmer
  • Science, Vol. 363, Issue 6425
  • DOI: 10.1126/science.aat4134

Bypassing the Kohn-Sham equations with machine learning
journal, October 2017


Numerical evidence of fluctuating stripes in the normal state of high- T c cuprate superconductors
journal, November 2017


Absence of Mott Transition in an Exact Solution of the Short-Range, One-Band Model in One Dimension
journal, July 1968


Cluster Dynamical Mean Field Theory of the Mott Transition
journal, October 2008


Majorana Positivity and the Fermion Sign Problem of Quantum Monte Carlo Simulations
journal, June 2016


Superconductivity and the Pseudogap in the Two-Dimensional Hubbard Model
journal, May 2013


Dynamical mean-field theory of strongly correlated fermion systems and the limit of infinite dimensions
journal, January 1996

  • Georges, Antoine; Kotliar, Gabriel; Krauth, Werner
  • Reviews of Modern Physics, Vol. 68, Issue 1
  • DOI: 10.1103/RevModPhys.68.13

Learning thermodynamics with Boltzmann machines
journal, October 2016


Ising Model for the λ Transition and Phase Separation in He 3 - He 4 Mixtures
journal, September 1971


Ising models of quantum frustration
journal, May 2001


Variational autoencoder analysis of Ising model statistical distributions and phase transitions
journal, March 2022


Electron correlations in narrow energy bands
journal, November 1963

  • Hubbard, J.
  • Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences, Vol. 276, Issue 1365, p. 238-257
  • DOI: 10.1098/rspa.1963.0204

Learning quantum phase transitions through topological data analysis
journal, December 2021


Self-learning Monte Carlo method and cumulative update in fermion systems
journal, June 2017


Valence-bond solid to antiferromagnet transition in the two-dimensional Su-Schrieffer-Heeger model by Langevin dynamics
journal, February 2022


Quantum Loop Topography for Machine Learning
journal, May 2017


Characterizing the three-orbital Hubbard model with determinant quantum Monte Carlo
journal, April 2016


Roadmap on Machine Learning in Electronic Structure
journal, February 2022


Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination
journal, June 2017


Quantum Monte Carlo Simulations of the 2D Su-Schrieffer-Heeger Model
journal, January 2021


Similarities between the Hubbard and Periodic Anderson Models at Finite Temperatures
journal, July 2000


Excitation spectra and correlation functions of quantum Su-Schrieffer-Heeger models
journal, June 2015


Topological origin of the fermion sign problem
journal, March 2016


Critical Behavior of an Ising Spin-Glass
journal, July 1986


Charge order and antiferromagnetism in the extended Hubbard model
journal, June 2019


Fast and scalable quantum Monte Carlo simulations of electron-phonon models
journal, June 2022