Paper · 2017 · Open access
Convolutional Gaussian Processes
Apollo (University of Cambridge), 30, 2849–2858 · Published 4 December 2017 · DOI 10.17863/cam.21271
In brief
“Convolutional Gaussian Processes” is a 2017 paper by Mark van der Wilk and 2 co-authors, published in Apollo (University of Cambridge). OpenAlex counts 44 citations as of 16 November 2026. It is open access: the full text is free to read at Apollo (University of Cambridge).
- Citations
- 44
- Most cited in
- 2020 (14)
- Field-weighted impact
- 3.19
- References
- 3
- Authors
- 3
Abstract
We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together with fast but accurate posterior inference. We investigate several variations of the convolutional kernel, and apply it to MNIST and CIFAR-10, which have both been known to be challenging for Gaussian processes. We also show how the marginal likelihood can be used to find an optimal weighting between convolutional and RBF kernels to further improve performance. We hope that this illustration of the usefulness of a marginal likelihood will help automate discovering architectures in larger models.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
van der Wilk, M., Rasmussen, C. E., & Hensman, J. J. (2017). Convolutional Gaussian Processes. Apollo (University of Cambridge), 30, 2849–2858. https://doi.org/10.17863/cam.21271
MLA 9
van der Wilk, Mark, et al. “Convolutional Gaussian Processes.” Apollo (University of Cambridge), vol. 30, 2017, pp. 2849–2858. https://doi.org/10.17863/cam.21271.
Chicago
van der Wilk, Mark, Carl Edward Rasmussen, and James J. Hensman. 2017. “Convolutional Gaussian Processes.” Apollo (University of Cambridge) 30: 2849–2858. https://doi.org/10.17863/cam.21271.
Harvard
van der Wilk, M., Rasmussen, C. E. and Hensman, J. J. (2017) ‘Convolutional Gaussian Processes’, Apollo (University of Cambridge), 30, pp. 2849–2858. doi:10.17863/cam.21271.
IEEE
M. van der Wilk, C. E. Rasmussen, and J. J. Hensman, “Convolutional Gaussian Processes,” Apollo (University of Cambridge), vol. 30, pp. 2849–2858, 2017, doi: 10.17863/cam.21271.
BibTeX
@article{vanderwilk2017convolutional,
title = {{Convolutional Gaussian Processes}},
author = {van der Wilk, Mark and Rasmussen, Carl Edward and Hensman, James J.},
journal = {Apollo (University of Cambridge)},
year = {2017},
volume = {30},
pages = {2849--2858},
doi = {10.17863/cam.21271},
url = {https://doi.org/10.17863/cam.21271}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2018 | 3 | |
| 2019 | 12 | |
| 2020 | 14 | |
| 2021 | 11 | |
| 2022 | 3 | |
| 2023 | 1 |
Its field-weighted citation impact is 3.19: it has been cited 3.19 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- convolution kernels
- posterior inference
- marginal likelihood
- kernel weighting
- Gaussian kernel
- image classification
- MNIST
- CIFAR-10
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
van der Wilk, M., Rasmussen, C. E., & Hensman, J. J. (2017). Convolutional Gaussian Processes. Apollo (University of Cambridge), 30, 2849–2858. https://doi.org/10.17863/cam.21271
How many times has this paper been cited?
44 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 Apollo (University of Cambridge).
Who wrote this paper?
Mark van der Wilk, Carl Edward Rasmussen, James J. Hensman.
What is the DOI of this paper?
10.17863/cam.21271. The permanent link is https://doi.org/10.17863/cam.21271.
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.