Conference paper · 2024 · Open access
Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)
Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), 22704 · Published 24 March 2024 · DOI 10.1609/aaai.v38i20.30604
In brief
“Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)” is a 2024 conference paper by Jian Li and 2 co-authors, published in Proceedings of the AAAI Conference on Artificial Intelligence. OpenAlex counts 0 citations as of 18 November 2026. It is open access: the full text is free to read at Proceedings of the AAAI Conference on Artificial Intelligence.
- Citations
- 0
- References
- 1
- Authors
- 3
Abstract
Kernel methods are powerful tools to capture nonlinear patterns behind given data but often lead to poor performance on complicated tasks compared to convolutional neural networks. The reason is that kernel methods are still shallow and fully connected models, failing to reveal hierarchical features and local interdependencies. In this paper, to acquire hierarchical and local knowledge, we incorporate kernel methods with deep architectures and convolutional operators in a spectral kernel learning framework. Based on the inverse Fourier transform and Rademacher complexity theory, we provide the generalization error bounds for the proposed model and prove that under suitable initialization, deeper networks lead to tighter error bounds. Inspired by theoretical findings, we finally completed the convolutional spectral kernel network (CSKN) with two additional regularizers and an initialization strategy. Extensive ablation results validate the effectiveness of non-stationary spectral kernel, multiple layers, additional regularizers, and the convolutional filters, which coincide with our theoretical findings. We further devise a VGG-type 8-layers CSKN, and it outperforms the existing kernel-based networks and popular CNN models on the medium-sized image classification tasks.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, J., Liu, Y., & Wang, W. (2024). Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), 22704. https://doi.org/10.1609/aaai.v38i20.30604
MLA 9
Li, Jian, et al. “Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint).” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 20, 2024, p. 22704. https://doi.org/10.1609/aaai.v38i20.30604.
Chicago
Li, Jian, Yong Liu, and Weiping Wang. 2024. “Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint).” Proceedings of the AAAI Conference on Artificial Intelligence 38 (20): 22704. https://doi.org/10.1609/aaai.v38i20.30604.
Harvard
Li, J., Liu, Y. and Wang, W. (2024) ‘Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)’, Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), p. 22704. doi:10.1609/aaai.v38i20.30604.
IEEE
J. Li, Y. Liu, and W. Wang, “Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint),” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 20, p. 22704, 2024, doi: 10.1609/aaai.v38i20.30604.
BibTeX
@inproceedings{li2024convolutional,
title = {{Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)}},
author = {Li, Jian and Liu, Yong and Wang, Weiping},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {20},
pages = {22704},
doi = {10.1609/aaai.v38i20.30604},
url = {https://doi.org/10.1609/aaai.v38i20.30604}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- kernel methods
- generalization bounds
- Rademacher complexity
- network depth
- initialization strategy
- regularization
- image classification
- hierarchical features
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?
Li, J., Liu, Y., & Wang, W. (2024). Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), 22704. https://doi.org/10.1609/aaai.v38i20.30604
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 Proceedings of the AAAI Conference on Artificial Intelligence: sign in and open the PDF from this page.
Who wrote this paper?
Jian Li, Yong Liu, Weiping Wang.
What is the DOI of this paper?
10.1609/aaai.v38i20.30604, permanently at https://doi.org/10.1609/aaai.v38i20.30604. 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.