- Physical Review Journals
All JournalsPhysics Magazine

Physical Review B

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Language-inspired machine learning approach for solving strongly correlated problems with dynamical mean-field theory

Hovan Lee1,*, Zelong Zhao2, George H. Booth2, Weifeng Ge3,†, and Cedric Weber2

  • *Contact author: hovan.lee@rhul.ac.uk
  • †Contact author: wfge@fudan.edu.cn
PDF

Phys. Rev. B 112, 035165 – Published 24 July, 2025

DOI: https://doi.org/10.1103/bk5q-pfb2

Abstract

We present SCALINN—strongly correlated approach with language-inspired neural network—as a method for solving the Anderson impurity model and reducing the computational cost of dynamical mean-field theory calculations. Inspired by the success of generative Transformer networks in natural language processing, SCALINN utilizes an in-house modified Transformer network in order to learn correlated Matsubara Green's functions, which act as solutions to the impurity model. This is achieved by providing the network with low-cost Matsubara Green's functions, thereby overcoming the computational cost of high accuracy solutions. Across different temperatures and interaction strengths, the performance of SCALINN is demonstrated in both physical observables (spectral function, Matsubara Green's functions, quasiparticle weight), and the mean squared error cost values of the neural network, showcasing the network's ability to accelerate Green's function based calculations of correlated materials by predicting DMFT solver solutions, which—given a sufficiently comprehensive training database—can be applied across materials and regimes, enabling ab initio DFT+DMFT calculations without prior knowledge of the material properties.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (50)

  1. A. Georges, G. Kotliar, W. Krauth, and M. J. Rozenberg, Exact functionals, effective actions and (dynamical) mean-field theories: Some remarks, Rev. Mod. Phys. 68, 13 (1996).
  2. G. Kotliar, S. Y. Savrasov, K. Haule, V. S. Oudovenko, O. Parcollet, and C. A. Marianetti, Electronic structure calculations with dynamical mean-field theory, Rev. Mod. Phys. 78, 865 (2006).
  3. H.-C. Jiang and T. P. Devereaux, Superconductivity in the doped Hubbard model and its interplay with next-nearest hopping t′, Science 365, 1424 (2019).
  4. M. Kheirkhah, Z. Yan, Y. Nagai, and F. Marsiglio, First-and second-order topological superconductivity and temperature-driven topological phase transitions in the extended Hubbard model with spin-orbit coupling, Phys. Rev. Lett. 125, 017001 (2020).
  5. A. Foley, S. Verret, A.-M. S. Tremblay, and D. Sénéchal, Coexistence of superconductivity and antiferromagnetism in the Hubbard model for cuprates, Phys. Rev. B 99, 184510 (2019).
  6. J. Koepsell, J. Vijayan, P. Sompet, F. Grusdt, T. A. Hilker, E. Demler, G. Salomon, I. Bloch, and C. Gross, Imaging magnetic polarons in the doped Fermi–Hubbard model, Nature (London) 572, 358 (2019).
  7. P. T. Brown, D. Mitra, E. Guardado-Sanchez, R. Nourafkan, A. Reymbaut, C.-D. Hébert, S. Bergeron, A.-M. Tremblay, J. Kokalj, D. A. Huse et al., Bad metallic transport in a cold atom Fermi-Hubbard system, Science 363, 379 (2019).
  8. B. Yang, H. Sun, R. Ott, H.-Y. Wang, T. V. Zache, J. C. Halimeh, Z.-S. Yuan, P. Hauke, and J.-W. Pan, Observation of gauge invariance in a 71-site Bose–Hubbard quantum simulator, Nature (London) 587, 392 (2020).
  9. C. Shao, E. V. Castro, S. Hu, and R. Mondaini, Interplay of local order and topology in the extended Haldane-Hubbard model, Phys. Rev. B 103, 035125 (2021).
  10. J. Fraxanet, D. González-Cuadra, T. Pfau, M. Lewenstein, T. Langen, and L. Barbiero, Topological quantum critical points in the extended Bose-Hubbard model, Phys. Rev. Lett. 128, 043402 (2022).
  11. D. González-Cuadra, A. Dauphin, P. R. Grzybowski, P. Wójcik, M. Lewenstein, and A. Bermudez, Symmetry-breaking topological insulators in the Bose-Hubbard model, Phys. Rev. B 99, 045139 (2019).
  12. C. Weber, D. D. O'Regan, N. D. M. Hine, P. B. Littlewood, G. Kotliar, and M. C. Payne, Importance of many-body effects in the kernel of hemoglobin for ligand binding, Phys. Rev. Lett. 110, 106402 (2013).
  13. P. W. Anderson, Localized magnetic states in metals, Phys. Rev. 124, 41 (1961).
  14. J. Hubbard, Electron correlations in narrow energy bands, Proc. Math. Phys. Eng. Sci. 276, 238 (1963).
  15. E. Gull, P. Werner, A. Millis, and M. Troyer, Performance analysis of continuous-time solvers for quantum impurity models, Phys. Rev. B 76, 235123 (2007).
  16. P. Werner and A. J. Millis, Hybridization expansion impurity solver: General formulation and application to Kondo lattice and two-orbital models, Phys. Rev. B 74, 155107 (2006).
  17. P. Werner, A. Comanac, L. de'Medici, M. Troyer, and A. J. Millis, Continuous-time solver for quantum impurity models, Phys. Rev. Lett. 97, 076405 (2006).
  18. A. N. Rubtsov, V. V. Savkin, and A. I. Lichtenstein, Continuous-time quantum Monte Carlo method for fermions, Phys. Rev. B 72, 035122 (2005).
  19. M. Caffarel and W. Krauth, Exact diagonalization approach to correlated fermions in infinite dimensions: Mott transition and superconductivity, Phys. Rev. Lett. 72, 1545 (1994).
  20. M. Capone, L. de'Medici, and A. Georges, Solving the dynamical mean-field theory at very low temperatures using the Lanczos exact diagonalization, Phys. Rev. B 76, 245116 (2007).
  21. A. Liebsch and H. Ishida, Temperature and bath size in exact diagonalization dynamical mean field theory, J. Phys.: Condens. Matter 24, 053201 (2012).
  22. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  23. Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature (London) 521, 436 (2015).
  24. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, Attention is all you need, in Advances in Neural Information Processing Systems, edited by I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates Inc., 2017), Vol. 30.
  25. V. Dunjko and H. J. Briegel, Machine learning and artificial intelligence in the quantum domain: A review of recent progress, Rep. Prog. Phys. 81, 074001 (2018).
  26. G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, N. Tishby, L. Vogt-Maranto, and L. Zdeborová, Machine learning and the physical sciences*, Rev. Mod. Phys. 91, 045002 (2019).
  27. J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko et al., Highly accurate protein structure prediction with AlphaFold, Nature (London) 596, 583 (2021).
  28. J. Kirkpatrick, B. McMorrow, D. H. Turban, A. L. Gaunt, J. S. Spencer, A. G. Matthews, A. Obika, L. Thiry, M. Fortunato, D. Pfau et al., Pushing the frontiers of density functionals by solving the fractional electron problem, Science 374, 1385 (2021).
  29. R. Fournier, L. Wang, O. V. Yazyev, and Q. Wu, Artificial neural network approach to the analytic continuation problem, Phys. Rev. Lett. 124, 056401 (2020).
  30. L.-F. Arsenault, A. Lopez-Bezanilla, O. A. von Lilienfeld, and A. J. Millis, Machine learning for many-body physics: The case of the Anderson impurity model, Phys. Rev. B 90, 155136 (2014).
  31. E. Sheridan, C. Rhodes, F. Jamet, I. Rungger, and C. Weber, Data-driven dynamical mean-field theory: An error-correction approach to solve the quantum many-body problem using machine learning, Phys. Rev. B 104, 205120 (2021).
  32. J. Rogers, T.-H. Lee, S. Pakdel, W. Xu, V. Dobrosavljevic, Y.-X. Yao, O. Christiansen, and N. Lanatà, Bypassing the computational bottleneck of quantum-embedding theories for strong electron correlations with machine learning, Phys. Rev. Res. 3, 013101 (2021).
  33. L. Boehnke, H. Hafermann, M. Ferrero, F. Lechermann, and O. Parcollet, Orthogonal polynomial representation of imaginary-time Green's functions, Phys. Rev. B 84, 075145 (2011).
  34. H. Shinaoka, J. Otsuki, M. Ohzeki, and K. Yoshimi, Compressing Green's function using intermediate representation between imaginary-time and real-frequency domains, Phys. Rev. B 96, 035147 (2017).
  35. J. Kaye, K. Chen, and O. Parcollet, Discrete Lehmann representation of imaginary time Green's functions, Phys. Rev. B 105, 235115 (2022).
  36. L. Arsenault, O. Von Lilienfeld, and A. Millis, Machine learning for many-body physics: Efficient solution of dynamical mean-field theory, arXiv:1506.08858.
  37. See Supplemental Material at http://link.aps.org/supplemental/10.1103/bk5q-pfb2 for taking note of the different positional encoding techniques in the concatenation and addition methods of the Matsubara frequencies.
  38. O. Parcollet, M. Ferrero, T. Ayral, H. Hafermann, I. Krivenko, L. Messio, and P. Seth, TRIQS: A toolbox for research on interacting quantum systems, Comput. Phys. Commun. 196, 398 (2015).
  39. A. Romero, D. Allan, B. Amadon, G. Antonius, T. Applencourt, L. Baguet, J. Bieder, F. Bottin, J. Bouchet, E. Bousquet, and Others, ABINIT: Overview and focus on selected capabilities, J. Chem. Phys. 152, 124102 (2020).
  40. E. Plekhanov, P. Hasnip, V. Sacksteder, M. Probert, S. J. Clark, K. Refson, and C. Weber, Many-body renormalization of forces in f-electron materials, Phys. Rev. B 98, 075129 (2018).
  41. E. J. Sturm, M. R. Carbone, D. Lu, A. Weichselbaum, and R. M. Konik, Predicting impurity spectral functions using machine learning, Phys. Rev. B 103, 245118 (2021).
  42. H. Kim, D. Kim, and D. Kim, Minimal neural network to learn the metal-insulator transition in the dynamical mean-field theory, New Physics: Sae Mulli 72, 487 (2022).
  43. J. B. Rigo and A. K. Mitchell, Machine learning effective models for quantum systems, Phys. Rev. B 101, 241105(R) (2020).
  44. C. Mejuto-Zaera, L. Zepeda-Núñez, M. Lindsey, N. Tubman, B. Whaley, and L. Lin, Efficient hybridization fitting for dynamical mean-field theory via semi-definite relaxation, Phys. Rev. B 101, 035143 (2020).
  45. M. Granath and H. U. R. Strand, Distributional exact diagonalization formalism for quantum impurity models, Phys. Rev. B 86, 115111 (2012).
  46. C. Weber, A. Amaricci, M. Capone, and P. B. Littlewood, Augmented hybrid exact-diagonalization solver for dynamical mean field theory, Phys. Rev. B 86, 115136 (2012).
  47. A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer, Automatic differentiation in PyTorch, Openreview (2017), https://openreview.net/forum?id=BJJsrmfCZ.
  48. N. Kavokine, H. Lu, T. Ayral, M. Ferrero, N. Wentzell, and O. Parcollet, CTSEG: A segment picture quantum impurity solver based on TRIQS, JOSS 10, 7425 (2025).
  49. Z. Zhao and H. Lee, Example database (2023), https://figshare.com/articles/dataset/Example_database/23144474.
  50. The code for SCALINN is available at https://github.com/zelong-zhao/SCALINN.

Outline

Information

Phys. Rev. B 112, 035165– Published 24 July, 2025
  • Received 2 April 2025
  • Revised 20 June 2025
  • Accepted 9 July 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation