Preprint · 2026 · Open access
Preconditioned Physics-Informed Neural Operator Training
arXiv (Cornell University) · Published 28 September 2026 · DOI 10.48550/arxiv.2609.36216
In brief
“Preconditioned Physics-Informed Neural Operator Training” is a 2026 preprint by Shizheng Wen and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 2
- Most cited in
- 2026 (2)
- References
- 18
- Authors
- 3
Abstract
Neural operators are typically trained in a supervised fashion, which requires a dataset to be generated with a classical solver. Training them physics-informed, i.e., purely from the governing equations, removes this large offline cost and allows fresh samples to be drawn at every optimization step, but has so far been limited to simplified problems and trails supervised training in accuracy. The obstacle is the ill-conditioning of physics-informed losses, which differential operators induce and which worsens as the discretization is refined. We therefore propose a preconditioned residual loss function and show mesh-independent conditioning for elliptic problems and greatly improved conditioning for saddle point problems. Realized through geometric and algebraic multigrid, the construction applies to linear and nonlinear equations, steady or time-dependent, on structured and unstructured meshes, is agnostic to the neural operator architecture, and adds no cost at inference. On the Poisson, Allen-Cahn and stationary Stokes equations, the resulting label-free training matches supervised training and is four to twenty-five times more accurate than previous physics-informed operator learning methods.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wen, S., Mishra, S., & Zeinhofer, M. (2026). Preconditioned Physics-Informed Neural Operator Training. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.36216
MLA 9
Wen, Shizheng, et al. “Preconditioned Physics-Informed Neural Operator Training.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.36216.
Chicago
Wen, Shizheng, Siddhartha Mishra, and Marius Zeinhofer. 2026. “Preconditioned Physics-Informed Neural Operator Training.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.36216.
Harvard
Wen, S., Mishra, S. and Zeinhofer, M. (2026) ‘Preconditioned Physics-Informed Neural Operator Training’, arXiv (Cornell University). doi:10.48550/arxiv.2609.36216.
IEEE
S. Wen, S. Mishra, and M. Zeinhofer, “Preconditioned Physics-Informed Neural Operator Training,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.36216.
BibTeX
@misc{wen2026preconditioned,
title = {{Preconditioned Physics-Informed Neural Operator Training}},
author = {Wen, Shizheng and Mishra, Siddhartha and Zeinhofer, Marius},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2609.36216},
url = {https://doi.org/10.48550/arxiv.2609.36216}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
- neural operators
- preconditioning
- ill-conditioning
- multigrid methods
- elliptic equations
- saddle point problems
- Allen-Cahn equation
- Poisson equation
Work with this paper
Most-cited papers in Physics and Astronomy
- Generalized Gradient Approximation Made SimpleJohn P. Perdew, Kieron Burke, Matthias Ernzerhof · Physical Review Letters · 1996 · 217,345 citations
- Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis setGeorg Kresse, Jürgen Furthmüller · Physical review. B, Condensed matter · 1996 · 125,164 citations
- Density-functional thermochemistry. III. The role of exact exchangeAxel D. Becke · The Journal of Chemical Physics · 1993 · 104,772 citations
- Development of the Colle-Salvetti correlation-energy formula into a functional of the electron densityChengteh Lee, Weitao Yang, Robert G. Parr · Physical review. B, Condensed matter · 1988 · 101,730 citations
- Projector augmented-wave methodPeter E. Blöchl · Physical review. B, Condensed matter · 1994 · 93,520 citations
Questions about this paper
How do I cite this paper in APA style?
Wen, S., Mishra, S., & Zeinhofer, M. (2026). Preconditioned Physics-Informed Neural Operator Training. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.36216
How many times has this paper been cited?
2 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Shizheng Wen, Siddhartha Mishra, Marius Zeinhofer.
What is the DOI of this paper?
10.48550/arxiv.2609.36216. The permanent link is https://doi.org/10.48550/arxiv.2609.36216.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.