Journal article · 2026 · Open access

Principled approaches for extending neural architectures to function spaces for operator learning

Julius Berner, Miguel Liu-Schiaffini, Jean Kossaifi, Valentin Duruisseaux, Boris Bonev, Kamyar Azizzadenesheli, Animashree Anandkumar

Nature Machine Intelligence, 8(7), 1173–1181 · Published 3 July 2026 · DOI 10.1038/s42256-026-01267-z

Open PDFView at the publisherCite this paper

In brief

“Principled approaches for extending neural architectures to function spaces for operator learning” is a 2026 journal article by Julius Berner and 6 co-authors, published in Nature Machine Intelligence. OpenAlex counts 37 citations as of 17 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Nature Machine Intelligence.

Citations
37
Most cited in
2026 (34)
Field-weighted impact
40.11
References
116
Authors
7

Abstract

Deep learning has achieved remarkable success in computer vision and natural language processing, where tasks are commonly formulated as mappings between finite-dimensional representations. Many scientific problems, however, including those governed by partial differential equations, are naturally posed on infinite-dimensional function spaces. This mismatch has limited conventional neural networks from achieving comparable success in scientific applications. Here we identify and distil key principles for constructing practical neural architectures for mappings between function spaces. Neural operators provide a principled extension of neural networks to such settings, offering a path towards bringing deep learning’s transformative impact to science. Because deep learning’s success has relied heavily on architectural refinements, extending these advances to neural operators allows operator learning to benefit from refined designs. Guided by the principles we outline, we propose a recipe for converting popular neural architectures into neural operators with minimal modifications. We also discuss practical steps for making these models effective. This perspective offers a systematic bridge between finite-dimensional network design and operator learning for scientific applications.

Cite this paper

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

APA 7

Berner, J., Liu-Schiaffini, M., Kossaifi, J., Duruisseaux, V., Bonev, B., Azizzadenesheli, K., & Anandkumar, A. (2026). Principled approaches for extending neural architectures to function spaces for operator learning. Nature Machine Intelligence, 8(7), 1173–1181. https://doi.org/10.1038/s42256-026-01267-z

MLA 9

Berner, Julius, et al. “Principled approaches for extending neural architectures to function spaces for operator learning.” Nature Machine Intelligence, vol. 8, no. 7, 2026, pp. 1173–1181. https://doi.org/10.1038/s42256-026-01267-z.

Chicago

Berner, Julius, Miguel Liu-Schiaffini, Jean Kossaifi, Valentin Duruisseaux, Boris Bonev, Kamyar Azizzadenesheli, and Animashree Anandkumar. 2026. “Principled approaches for extending neural architectures to function spaces for operator learning.” Nature Machine Intelligence 8 (7): 1173–1181. https://doi.org/10.1038/s42256-026-01267-z.

Harvard

Berner, J. et al. (2026) ‘Principled approaches for extending neural architectures to function spaces for operator learning’, Nature Machine Intelligence, 8(7), pp. 1173–1181. doi:10.1038/s42256-026-01267-z.

IEEE

J. Berner et al., “Principled approaches for extending neural architectures to function spaces for operator learning,” Nature Machine Intelligence, vol. 8, no. 7, pp. 1173–1181, 2026, doi: 10.1038/s42256-026-01267-z.

BibTeX

@article{berner2026principled,
  title     = {{Principled approaches for extending neural architectures to function spaces for operator learning}},
  author    = {Berner, Julius and Liu-Schiaffini, Miguel and Kossaifi, Jean and Duruisseaux, Valentin and Bonev, Boris and Azizzadenesheli, Kamyar and Anandkumar, Animashree},
  journal   = {Nature Machine Intelligence},
  year      = {2026},
  volume    = {8},
  number    = {7},
  pages     = {1173--1181},
  doi       = {10.1038/s42256-026-01267-z},
  url       = {https://doi.org/10.1038/s42256-026-01267-z}
}

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
  • operator learning
  • infinite-dimensional function spaces
  • neural network design
  • partial differential equations
  • scientific machine learning

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?

Berner, J., Liu-Schiaffini, M., Kossaifi, J., Duruisseaux, V., Bonev, B., Azizzadenesheli, K., & Anandkumar, A. (2026). Principled approaches for extending neural architectures to function spaces for operator learning. Nature Machine Intelligence, 8(7), 1173–1181. https://doi.org/10.1038/s42256-026-01267-z

How many times has this paper been cited?

37 times, according to OpenAlex on 17 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 at Nature Machine Intelligence: sign in and open the PDF from this page.

Who wrote this paper?

Julius Berner, Miguel Liu-Schiaffini, Jean Kossaifi, Valentin Duruisseaux, Boris Bonev, Kamyar Azizzadenesheli, Animashree Anandkumar.

What is the DOI of this paper?

10.1038/s42256-026-01267-z, permanently at https://doi.org/10.1038/s42256-026-01267-z. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.