Preprint · 2018 · Open access

Deep Convolutional Networks as shallow Gaussian Processes

Adrià Garriga-Alonso, Laurence Aitchison, Carl Edward Rasmussen

arXiv (Cornell University), 1–16 · Published 16 August 2018 · DOI 10.17863/cam.42340

Free PDFView at the publisherCite this paper

In brief

“Deep Convolutional Networks as shallow Gaussian Processes” is a 2018 preprint by Adrià Garriga-Alonso and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 232 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
232
Most cited in
2021 (54)
References
29
Authors
3

Abstract

We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very few parameters: only the hyperparameters of the original CNN. Further, we show that this kernel has two properties that allow it to be computed efficiently; the cost of evaluating the kernel for a pair of images is similar to a single forward pass through the original CNN with only one filter per layer. The kernel equivalent to a 32-layer ResNet obtains 0.84% classification error on MNIST, a new record for GPs with a comparable number of parameters.

Cite this paper

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

APA 7

Garriga-Alonso, A., Aitchison, L., & Rasmussen, C. E. (2018). Deep Convolutional Networks as shallow Gaussian Processes. arXiv (Cornell University), 1–16. https://doi.org/10.17863/cam.42340

MLA 9

Garriga-Alonso, Adrià, et al. “Deep Convolutional Networks as shallow Gaussian Processes.” arXiv (Cornell University), 2018, pp. 1–16. https://doi.org/10.17863/cam.42340.

Chicago

Garriga-Alonso, Adrià, Laurence Aitchison, and Carl Edward Rasmussen. 2018. “Deep Convolutional Networks as shallow Gaussian Processes.” arXiv (Cornell University): 1–16. https://doi.org/10.17863/cam.42340.

Harvard

Garriga-Alonso, A., Aitchison, L. and Rasmussen, C. E. (2018) ‘Deep Convolutional Networks as shallow Gaussian Processes’, arXiv (Cornell University), pp. 1–16. doi:10.17863/cam.42340.

IEEE

A. Garriga-Alonso, L. Aitchison, and C. E. Rasmussen, “Deep Convolutional Networks as shallow Gaussian Processes,” arXiv (Cornell University), pp. 1–16, 2018, doi: 10.17863/cam.42340.

BibTeX

@misc{garrigaalonso2018deep,
  title     = {{Deep Convolutional Networks as shallow Gaussian Processes}},
  author    = {Garriga-Alonso, Adrià and Aitchison, Laurence and Rasmussen, Carl Edward},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  pages     = {1--16},
  doi       = {10.17863/cam.42340},
  url       = {https://doi.org/10.17863/cam.42340}
}

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

Citations by year

YearCitationsShare of the best year
201855
20193131
20204343
20215454
20222929
20232929
20242222
202588
20261111

Topic and keywords

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

  • deep Gaussian processes
  • convolutional neural networks
  • ResNet
  • infinite-width limit
  • kernel approximation
  • kernel methods
  • image classification
  • MNIST

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?

Garriga-Alonso, A., Aitchison, L., & Rasmussen, C. E. (2018). Deep Convolutional Networks as shallow Gaussian Processes. arXiv (Cornell University), 1–16. https://doi.org/10.17863/cam.42340

How many times has this paper been cited?

232 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?

Adrià Garriga-Alonso, Laurence Aitchison, Carl Edward Rasmussen.

What is the DOI of this paper?

10.17863/cam.42340. The permanent link is https://doi.org/10.17863/cam.42340.

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.