Preprint · 2021 · Open access

Approximation and Learning with Deep Convolutional Models: a Kernel Perspective

Alberto Bietti

arXiv (Cornell University) · Published 19 February 2021 · DOI 10.48550/arxiv.2102.10032

Open PDFView at the publisherCite this paper

In brief

“Approximation and Learning with Deep Convolutional Models: a Kernel Perspective” is a 2021 preprint by Alberto Bietti, published in arXiv (Cornell University). OpenAlex counts 19 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
19
Most cited in
2021 (6)
References
71
Authors
1

Abstract

The empirical success of deep convolutional networks on tasks involving high-dimensional data such as images or audio suggests that they can efficiently approximate certain functions that are well-suited for such tasks. In this paper, we study this through the lens of kernel methods, by considering simple hierarchical kernels with two or three convolution and pooling layers, inspired by convolutional kernel networks. These achieve good empirical performance on standard vision datasets, while providing a precise description of their functional space that yields new insights on their inductive bias. We show that the RKHS consists of additive models of interaction terms between patches, and that its norm encourages spatial similarities between these terms through pooling layers. We then provide generalization bounds which illustrate how pooling and patches yield improved sample complexity guarantees when the target function presents such regularities.

Cite this paper

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

APA 7

Bietti, A. (2021). Approximation and Learning with Deep Convolutional Models: a Kernel Perspective. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2102.10032

MLA 9

Bietti, Alberto. “Approximation and Learning with Deep Convolutional Models: a Kernel Perspective.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2102.10032.

Chicago

Bietti, Alberto. 2021. “Approximation and Learning with Deep Convolutional Models: a Kernel Perspective.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2102.10032.

Harvard

Bietti, A. (2021) ‘Approximation and Learning with Deep Convolutional Models: a Kernel Perspective’, arXiv (Cornell University). doi:10.48550/arxiv.2102.10032.

IEEE

A. Bietti, “Approximation and Learning with Deep Convolutional Models: a Kernel Perspective,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2102.10032.

BibTeX

@misc{bietti2021approximation,
  title     = {{Approximation and Learning with Deep Convolutional Models: a Kernel Perspective}},
  author    = {Bietti, Alberto},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  doi       = {10.48550/arxiv.2102.10032},
  url       = {https://doi.org/10.48550/arxiv.2102.10032}
}

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

Citations by year

YearCitationsShare of the best year
202166
202255
202322
202455
202511

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques

  • deep convolutional neural networks
  • kernel methods
  • reproducing kernel Hilbert space
  • inductive bias
  • pooling layers
  • generalization bounds
  • sample complexity
  • function approximation

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?

Bietti, A. (2021). Approximation and Learning with Deep Convolutional Models: a Kernel Perspective. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2102.10032

How many times has this paper been cited?

19 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?

Alberto Bietti.

What is the DOI of this paper?

10.48550/arxiv.2102.10032, permanently at https://doi.org/10.48550/arxiv.2102.10032. 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.