Conference paper · 2021 · Open access

Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels

Andrey P. Demichev

International Workshop on Deep Learning in Computational Physics (DLCP), 002 · Published 1 December 2021 · DOI 10.22323/1.410.0002

Open PDFView at the publisherCite this paper

In brief

“Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels” is a 2021 conference paper by Andrey P. Demichev, published in International Workshop on Deep Learning in Computational Physics (DLCP). OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at International Workshop on Deep Learning in Computational Physics (DLCP).

Citations
0
References
32
Authors
1

Abstract

In this work we establish a relationship between the many-channel limit for $SO(2)$-equivariant convolutional neural networks (CNNs) and the corresponding equivariant Gaussian process (GP) in the case of Fourier space quadratic nonlinearity. The approach used provides explicit equivariance at each step of the relationship derivation.

Cite this paper

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

APA 7

Demichev, A. P. (2021). Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels. International Workshop on Deep Learning in Computational Physics (DLCP), 002. https://doi.org/10.22323/1.410.0002

MLA 9

Demichev, Andrey P. “Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels.” International Workshop on Deep Learning in Computational Physics (DLCP), 2021, p. 002. https://doi.org/10.22323/1.410.0002.

Chicago

Demichev, Andrey P. 2021. “Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels.” International Workshop on Deep Learning in Computational Physics (DLCP): 002. https://doi.org/10.22323/1.410.0002.

Harvard

Demichev, A. P. (2021) ‘Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels’, International Workshop on Deep Learning in Computational Physics (DLCP), p. 002. doi:10.22323/1.410.0002.

IEEE

A. P. Demichev, “Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels,” International Workshop on Deep Learning in Computational Physics (DLCP), p. 002, 2021, doi: 10.22323/1.410.0002.

BibTeX

@inproceedings{demichev2021equivariant,
  title     = {{Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels}},
  author    = {Demichev, Andrey P.},
  booktitle = {International Workshop on Deep Learning in Computational Physics (DLCP)},
  year      = {2021},
  pages     = {002},
  doi       = {10.22323/1.410.0002},
  url       = {https://doi.org/10.22323/1.410.0002}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference

  • convolutional neural networks
  • equivariance

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Demichev, A. P. (2021). Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels. International Workshop on Deep Learning in Computational Physics (DLCP), 002. https://doi.org/10.22323/1.410.0002

How many times has this paper been cited?

0 times, according to OpenAlex on 18 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 International Workshop on Deep Learning in Computational Physics (DLCP): sign in and open the PDF from this page.

Who wrote this paper?

Andrey P. Demichev.

What is the DOI of this paper?

10.22323/1.410.0002, permanently at https://doi.org/10.22323/1.410.0002. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.