- Physical Review Journals
All JournalsPhysics Magazine

Physical Review D

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

Addressing the sign problem in Euclidean path integrals with radial basis function neural networks

Gábor Balassa

PDF

Phys. Rev. D 113, 016022 – Published 26 January, 2026

DOI: https://doi.org/10.1103/74r8-vkm9

Abstract

Solving interacting field theories at finite densities remains a numerically and conceptually challenging task, even with modern computational capabilities. In this paper, we propose a novel approach based on an expansion of the Euclidean path integrals using radial basis function neural networks, which allows the calculation of observables at finite densities and overcomes the sign problem in a numerically very efficient manner. The method is applied to an interacting complex scalar field theory at finite chemical potential in 3+1 dimensions, which exhibits both the sign problem and the silver blaze phenomenon, similar to QCD. The critical chemical potential at which phase transition occurs is estimated to be μc=1.17±0.018, and the silver blaze problem is accurately described below μc.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (30)

  1. T. D. Cohen, Functional integrals for QCD at nonzero chemical potential and zero density, Phys. Rev. Lett. 91, 222001 (2003).
  2. M. Troyer and U.-J. Wiese, Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations, Phys. Rev. Lett. 94, 170201 (2005).
  3. Z. Fodor and S. Katz, A new method to study lattice QCD at finite temperature and chemical potential, Phys. Lett. B 534, 87 (2002).
  4. P. de Forcrand and O. Philipsen, The QCD phase diagram for small densities from imaginary chemical potential, Nucl. Phys. B642, 290 (2002).
  5. M. D’Elia and M.-P. Lombardo, Finite density QCD via an imaginary chemical potential, Phys. Rev. D 67, 014505 (2003).
  6. Z. Fodor, S. D. Katz, and C. Schmidt, The density of states method at non-zero chemical potential, J. High Energy Phys. 03 (2007) 121.
  7. G. Aarts and I.-O. Stamatescu, Stochastic quantization at finite chemical potential, J. High Energy Phys. 09 (2008) 018.
  8. J. Berges, S. Borsányi, D. Sexty, and I.-O. Stamatescu, Lattice simulations of real-time quantum fields, Phys. Rev. D 75, 045007 (2007).
  9. J. Berges and D. Sexty, Real-time gauge theory simulations from stochastic quantization with optimized updating, Nucl. Phys. B799, 306 (2008).
  10. 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).
  11. Y. Che, C. Gneiting, and F. Nori, Estimating the euclidean quantum propagator with deep generative modeling of Feynman paths, Phys. Rev. B 105, 214205 (2022).
  12. J. M. Martyn, K. Najafi, and D. Luo, Variational neural-network ansatz for continuum quantum field theory, Phys. Rev. Lett. 131, 081601 (2023).
  13. G. Balassa, On the solution of euclidean path integrals with neural networks, arXiv:2509.16953.
  14. K. Nagata, Finite-density lattice QCD and sign problem: Current status and open problems, Prog. Part. Nucl. Phys. 127, 103991 (2022).
  15. M. Troyer and U.-J. Wiese, Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations, Phys. Rev. Lett. 94, 170201 (2005).
  16. G. Aarts, Complex Langevin dynamics at finite chemical potential: Mean field analysis in the relativistic Bose gas, J. High Energy Phys. 05 (2009) 052.
  17. M. G. Endres, Method for simulating o(n) lattice models at finite density, Phys. Rev. D 75, 065012 (2007).
  18. C. Gattringer and T. Kloiber, Lattice study of the silver blaze phenomenon for a charged scalar ϕ4 field, Nucl. Phys. B869, 56 (2013).
  19. G. Balassa, Fixed-energy inverse scattering with radial basis function neural networks and its application to neutron–α interactions, Prog. Theor. Exp. Phys. 2023, 113A01 (2023).
  20. C. Shao, Data classification by quantum radial-basis-function networks, Phys. Rev. A 102, 042418 (2020).
  21. G. Balassa, Neural network approximation of euclidean path integrals and its application for the ϕ4 theory in 1+1 dimensions, arXiv:2509.18785.
  22. H. Akaike, A new look at the statistical model identification, IEEE Trans. Autom. Control 19, 716 (1974).
  23. J. M. Pawlowski, I.-O. Stamatescu, and F. P. Ziegler, Cooling stochastic quantization with colored noise, Phys. Rev. D 96, 114505 (2017).
  24. D. Schaich and W. Loinaz, Improved lattice measurement of the critical coupling in ϕ24 theory, Phys. Rev. D 79, 056008 (2009).
  25. P. B. Arnold and O. Espinosa, The effective potential and first order phase transitions: Beyond leading-order, Phys. Rev. D 47, 3546 (1993); 50, 6662(E) (1994).
  26. D. J. E. Callaway and D. J. Maloof, Effective potential of lattice ϕ4 theory, Phys. Rev. D 27, 406 (1983).
  27. N. Straumann, Cosmological phase transitions, arXiv:astro-ph/0409042.
  28. H. Mukaida and Y. Shimada, Convex effective potential of o(n)-symmetricø4 theory for large n, Nucl. Phys. B479, 663 (1996).
  29. J. Alexandre, Spontaneous symmetry breaking and linear effective potentials, Phys. Rev. D 86, 025028 (2012).
  30. G. Aarts, Can stochastic quantization evade the sign problem? The relativistic Bose gas at finite chemical potential, Phys. Rev. Lett. 102, 131601 (2009).

Outline

Information

Phys. Rev. D 113, 016022– Published 26 January, 2026
  • Received 2 October 2025
  • Accepted 8 January 2026
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. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation