Preprint · 2016 · Open access
Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size
arXiv (Cornell University), 1 · Published 1 January 2016
In brief
“Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size” is a 2016 preprint by Jongsoo Park and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 32 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 32
- Most cited in
- 2019 (8)
- Authors
- 6
Abstract
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels. We present a method to realize simultaneously size economy and speed improvement while pruning CNNs. Paramount to our success is an efficient general sparse-with-dense matrix multiplication implementation that is applicable to convolution of feature maps with kernels of arbitrary sparsity patterns. Complementing this, we developed a performance model that predicts sweet spots of sparsity levels for different layers and on different computer architectures. Together, these two allow us to demonstrate 3.1--7.3$\times$ convolution speedups over dense convolution in AlexNet, on Intel Atom, Xeon, and Xeon Phi processors, spanning the spectrum from mobile devices to supercomputers. We also open source our project at this https URL.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Park, J., Li, S. R., Wen, W. X., Li, H., Chen, Y., & Dubey, P. K. (2016). Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size. arXiv (Cornell University), 1. https://arxiv.org/pdf/1608.01409
MLA 9
Park, Jongsoo, et al. “Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size.” arXiv (Cornell University), vol. 1, 2016. https://arxiv.org/pdf/1608.01409.
Chicago
Park, Jongsoo, Sheng R. Li, Wei Xiong Wen, Hai Li, Yiran Chen, and Pradeep Kumar Dubey. 2016. “Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size.” arXiv (Cornell University) 1. https://arxiv.org/pdf/1608.01409.
Harvard
Park, J. et al. (2016) ‘Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size’, arXiv (Cornell University), 1. Available at: https://arxiv.org/pdf/1608.01409.
IEEE
J. Park, S. R. Li, W. X. Wen, H. Li, Y. Chen, and P. K. Dubey, “Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size,” arXiv (Cornell University), vol. 1, 2016.
BibTeX
@misc{park2016holistic,
title = {{Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size}},
author = {Park, Jongsoo and Li, Sheng R. and Wen, Wei Xiong and Li, Hai and Chen, Yiran and Dubey, Pradeep Kumar},
howpublished = {arXiv (Cornell University)},
year = {2016},
volume = {1},
url = {https://arxiv.org/pdf/1608.01409}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 2 | |
| 2018 | 3 | |
| 2019 | 8 | |
| 2020 | 7 | |
| 2021 | 6 | |
| 2022 | 3 | |
| 2023 | 1 | |
| 2024 | 1 | |
| 2025 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- sparse convolutional neural networks
- sparse matrix multiplication
- sparse kernels
- inference acceleration
- model size reduction
- performance modeling
- heterogeneous architectures
- Intel Xeon Phi
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?
Park, J., Li, S. R., Wen, W. X., Li, H., Chen, Y., & Dubey, P. K. (2016). Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size. arXiv (Cornell University), 1. https://arxiv.org/pdf/1608.01409
How many times has this paper been cited?
32 times, according to OpenAlex on 19 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 full text from this page.
Who wrote this paper?
Jongsoo Park, Sheng R. Li, Wei Xiong Wen, Hai Li, Yiran Chen, Pradeep Kumar Dubey.
Bibliographic data from OpenAlex (CC0), last checked 19 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.