Preprint · 2026 · Open access
Gaussian equivalence for CNN with non-Gaussian weights
arXiv (Cornell University) · Published 19 October 2026 · DOI 10.48550/arxiv.2610.25928
In brief
“Gaussian equivalence for CNN with non-Gaussian weights” is a 2026 preprint by Federico Bassetti and Vassili De Palma, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 17
- Authors
- 2
Abstract
We study the infinite-width limit of convolutional neural networks with random weights and show that the Gaussian process limit does not require Gaussian priors. Assuming that the weights are i.i.d., centered, and have sufficiently many finite moments, converges weakly in the space of continuous functions on the compact input set to independent copies of a centered Gaussian process. Our framework accommodates activation functions of polynomial growth together with a broad class of patch-extraction operators, covering standard convolutions, padding, stride, and common pooling mechanisms.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Bassetti, F., & De Palma, V. (2026). Gaussian equivalence for CNN with non-Gaussian weights. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.25928
MLA 9
Bassetti, Federico, and Vassili De Palma. “Gaussian equivalence for CNN with non-Gaussian weights.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.25928.
Chicago
Bassetti, Federico and Vassili De Palma. 2026. “Gaussian equivalence for CNN with non-Gaussian weights.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.25928.
Harvard
Bassetti, F. and De Palma, V. (2026) ‘Gaussian equivalence for CNN with non-Gaussian weights’, arXiv (Cornell University). doi:10.48550/arxiv.2610.25928.
IEEE
F. Bassetti and V. De Palma, “Gaussian equivalence for CNN with non-Gaussian weights,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.25928.
BibTeX
@misc{bassetti2026gaussian,
title = {{Gaussian equivalence for CNN with non-Gaussian weights}},
author = {Bassetti, Federico and De Palma, Vassili},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2610.25928},
url = {https://doi.org/10.48550/arxiv.2610.25928}
}
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
- infinite-width limit
- convolutional neural networks
- random weights
- non-Gaussian priors
- Gaussian process limit
- weak convergence
- polynomial activation functions
- pooling
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?
Bassetti, F., & De Palma, V. (2026). Gaussian equivalence for CNN with non-Gaussian weights. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.25928
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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Federico Bassetti, Vassili De Palma.
What is the DOI of this paper?
10.48550/arxiv.2610.25928, permanently at https://doi.org/10.48550/arxiv.2610.25928. 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.