Preprint · 2023 · Open access

Can Physics Informed Neural Operators Self Improve?

Ritam Majumdar, Amey Varhade, Shirish Subhash Karande, Lovekesh Vig

arXiv (Cornell University) · Published 23 November 2023 · DOI 10.48550/arxiv.2311.13885

Free PDFView at the publisherCite this paper

In brief

“Can Physics Informed Neural Operators Self Improve?” is a 2023 preprint by Ritam Majumdar and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 16 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2024 (1)
References
4
Authors
4

Abstract

Self-training techniques have shown remarkable value across many deep learning models and tasks. However, such techniques remain largely unexplored when considered in the context of learning fast solvers for systems of partial differential equations (Eg: Neural Operators). In this work, we explore the use of self-training for Fourier Neural Operators (FNO). Neural Operators emerged as a data driven technique, however, data from experiments or traditional solvers is not always readily available. Physics Informed Neural Operators (PINO) overcome this constraint by utilizing a physics loss for the training, however the accuracy of PINO trained without data does not match the performance obtained by training with data. In this work we show that self-training can be used to close this gap in performance. We examine canonical examples, namely the 1D-Burgers and 2D-Darcy PDEs, to showcase the efficacy of self-training. Specifically, FNOs, when trained exclusively with physics loss through self-training, approach 1.07x for Burgers and 1.02x for Darcy, compared to FNOs trained with both data and physics loss. Furthermore, we discover that pseudo-labels can be used for self-training without necessarily training to convergence in each iteration. A consequence of this is that we are able to discover self-training schedules that improve upon the baseline performance of PINO in terms of accuracy as well as time.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Majumdar, R., Varhade, A., Karande, S. S., & Vig, L. (2023). Can Physics Informed Neural Operators Self Improve? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.13885

MLA 9

Majumdar, Ritam, et al. “Can Physics Informed Neural Operators Self Improve?” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2311.13885.

Chicago

Majumdar, Ritam, Amey Varhade, Shirish Subhash Karande, and Lovekesh Vig. 2023. “Can Physics Informed Neural Operators Self Improve?” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.13885.

Harvard

Majumdar, R. et al. (2023) ‘Can Physics Informed Neural Operators Self Improve?’, arXiv (Cornell University). doi:10.48550/arxiv.2311.13885.

IEEE

R. Majumdar, A. Varhade, S. S. Karande, and L. Vig, “Can Physics Informed Neural Operators Self Improve?,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2311.13885.

BibTeX

@misc{majumdar2023physics,
  title     = {{Can Physics Informed Neural Operators Self Improve?}},
  author    = {Majumdar, Ritam and Varhade, Amey and Karande, Shirish Subhash and Vig, Lovekesh},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2311.13885},
  url       = {https://doi.org/10.48550/arxiv.2311.13885}
}

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

  • physics-informed neural operators
  • self-training
  • Fourier neural operator
  • pseudo-labeling
  • partial differential equations
  • fast solvers

Work with this paper

Most-cited papers in Physics and Astronomy

All highly cited Physics and Astronomy papers

Questions about this paper

How do I cite this paper in APA style?

Majumdar, R., Varhade, A., Karande, S. S., & Vig, L. (2023). Can Physics Informed Neural Operators Self Improve? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.13885

How many times has this paper been cited?

1 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?

Ritam Majumdar, Amey Varhade, Shirish Subhash Karande, Lovekesh Vig.

What is the DOI of this paper?

10.48550/arxiv.2311.13885. The permanent link is https://doi.org/10.48550/arxiv.2311.13885.

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.