EUVIMEDEUVIMED entdecken
Crossref

DeepONet Based Preconditioning Strategies for Solving Parametric Linear Systems of Equations

Alena Kopaničáková, George Em Karniadakis

SIAM Journal on Scientific Computing · 28.02.2025 · 47 (1) · C151-C181

DOI: 10.1137/24m162861x ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 20.02.2025. Verfasst von Alena Kopaničáková und 1 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Platform for Advanced Scientific Computing, DOE SEA-CROGS, MURI-AFOSR.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a new class of hybrid preconditioners for solving parametric linear systems of equations. The proposed preconditioners are constructed by hybridizing the deep operator network, namely, DeepONet, with standard iterative methods. Exploiting the spectral bias, DeepONet-based components are harnessed to address low-frequency error components, while conventional iterative methods are employed to mitigate high-frequency error components. Our preconditioning framework comprises two distinct hybridization approaches: direct preconditioning (DP) and trunk basis (TB). In the DP approach, DeepONet is used to approximate an action of an inverse operator to a vector during each preconditioning step. In contrast, the TB approach extracts basis functions from the trained DeepONet to construct a map to a smaller subspace, in which the low-frequency component of the error can be effectively eliminated. Our numerical results demonstrate that utilizing the TB approach enhances the convergence of Krylov methods by a large margin compared to standard nonhybrid preconditioning strategies. Moreover, the proposed hybrid preconditioners exhibit robustness across a wide range of model parameters and problem resolutions.

Förderung

  • Platform for Advanced Scientific Computing
  • DOE SEA-CROGS
  • MURI-AFOSR
  • ONR-Vannevar Bush Faculty Fellowship
  • Ansys, Inc.
  • Swiss National Science Foundation

Zitieren

APA

Kopaničáková, A., & Karniadakis, G. E. (2025). DeepONet Based Preconditioning Strategies for Solving Parametric Linear Systems of Equations. SIAM Journal on Scientific Computing, 47(1), C151-C181. https://doi.org/10.1137/24m162861x

Vancouver

Kopaničáková A, Karniadakis GE. DeepONet Based Preconditioning Strategies for Solving Parametric Linear Systems of Equations. SIAM Journal on Scientific Computing. 2025;47(1):C151-C181. doi:10.1137/24m162861x

BibTeX
@article{Kopanikov2025,
  author = {Kopaničáková, Alena and Karniadakis, George Em},
  title = {DeepONet Based Preconditioning Strategies for Solving Parametric Linear Systems of Equations},
  journal = {SIAM Journal on Scientific Computing},
  year = {2025},
  volume = {47},
  number = {1},
  pages = {C151--C181},
  doi = {10.1137/24m162861x}
}
Kostenlos starten →