Preprint · 2026 · Open access

Large deviation principles for convolutional Bayesian neural networks

Federico Bassetti, Vassili De Palma, Lucia Ladelli

arXiv (Cornell University) · Published 6 March 2026 · DOI 10.48550/arxiv.2603.06023

Open PDFView at the publisherCite this paper

In brief

“Large deviation principles for convolutional Bayesian neural networks” is a 2026 preprint by Federico Bassetti and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
14
Authors
3

Abstract

While suitably scaled CNNs with Gaussian initialization are known to converge to Gaussian processes as the number of channels diverges, little is known beyond this Gaussian limit. We establish a large deviation principle (LDP) for convolutional neural networks in the infinite-channel regime. We consider a broad class of multidimensional CNN architectures characterized by general receptive fields encoded through a patch-extractor function satisfying mild structural assumptions. Our main result establishes a large deviation principle (LDP) for the sequence of conditional covariance matrices under Gaussian prior distribution on the weights. We further derive an LDP for the posterior distribution obtained by conditioning on a finite number of observations. In addition, we provide a streamlined proof of the concentration of the conditional covariances and of the Gaussian equivalence of the network. To the best of our knowledge, this is the first large deviation principle established for convolutional neural networks.

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., & Ladelli, L. (2026). Large deviation principles for convolutional Bayesian neural networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06023

MLA 9

Bassetti, Federico, et al. “Large deviation principles for convolutional Bayesian neural networks.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.06023.

Chicago

Bassetti, Federico, Vassili De Palma, and Lucia Ladelli. 2026. “Large deviation principles for convolutional Bayesian neural networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06023.

Harvard

Bassetti, F., De Palma, V. and Ladelli, L. (2026) ‘Large deviation principles for convolutional Bayesian neural networks’, arXiv (Cornell University). doi:10.48550/arxiv.2603.06023.

IEEE

F. Bassetti, V. De Palma, and L. Ladelli, “Large deviation principles for convolutional Bayesian neural networks,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.06023.

BibTeX

@misc{bassetti2026large,
  title     = {{Large deviation principles for convolutional Bayesian neural networks}},
  author    = {Bassetti, Federico and De Palma, Vassili and Ladelli, Lucia},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2603.06023},
  url       = {https://doi.org/10.48550/arxiv.2603.06023}
}

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

  • large deviations
  • convolutional neural networks
  • Gaussian processes
  • Bayesian neural networks
  • posterior distribution
  • receptive fields

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?

Bassetti, F., De Palma, V., & Ladelli, L. (2026). Large deviation principles for convolutional Bayesian neural networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06023

How many times has this paper been cited?

1 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, Lucia Ladelli.

What is the DOI of this paper?

10.48550/arxiv.2603.06023, permanently at https://doi.org/10.48550/arxiv.2603.06023. 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.