EUVIMEDEUVIMED entdecken
Crossref

Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory

Yixuan Sun, Srinivas Eswar, Yin Lin, William Detmold, Phiala Shanahan, Yang Liu, Xiaoye Li, Prasanna Balaprakash

ACM Transactions on AI for Science · 2026

DOI: 10.1145/3841473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on AI for Science, 2026. Verfasst von Yixuan Sun und 7 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics (QCD). Solving the Hermitian positive definite systems, which are sparse but ill-conditioned, involves using iterative methods, such as Conjugate Gradient (CG), which are time-consuming and computationally expensive. Preconditioners can effectively accelerate this process, with the state-of-the-art being multigrid preconditioners. However, constructing useful preconditioners can be challenging, adding additional computational overhead, especially in large linear systems. We propose a framework, leveraging operator learning techniques, to construct linear maps as effective preconditioners. The method in this work does not rely on explicit matrices from either the original linear systems or the produced preconditioners, allowing efficient model training and application in the CG solver. In the context of the Schwinger model ( \(U(1)\) gauge theory in 1+1 spacetime dimensions with two degenerate-mass fermions), this preconditioning scheme effectively decreases the condition number of the linear systems and approximately halves the number of iterations required for convergence in relevant parameter ranges. We further demonstrate the framework learns a general mapping dependent on the lattice structure which leads to zero-shot learning ability for the Dirac operators constructed from gauge field configurations of different sizes.

Zitieren

APA

Sun, Y., Eswar, S., Lin, Y., Detmold, W., Shanahan, P., Liu, Y., Li, X., & Balaprakash, P. (2026). Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory. ACM Transactions on AI for Science. https://doi.org/10.1145/3841473

Vancouver

Sun Y, Eswar S, Lin Y, Detmold W, Shanahan P, Liu Y, et al. Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory. ACM Transactions on AI for Science. 2026. doi:10.1145/3841473

BibTeX
@article{Sun2026,
  author = {Sun, Yixuan and Eswar, Srinivas and Lin, Yin and Detmold, William and Shanahan, Phiala and Liu, Yang and Li, Xiaoye and Balaprakash, Prasanna},
  title = {Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory},
  journal = {ACM Transactions on AI for Science},
  year = {2026},
  doi = {10.1145/3841473}
}
Kostenlos starten →