Preprint · 2019 · Open access

DEEP-BO for Hyperparameter Optimization of Deep Networks

Hyunghun Cho, Kim, Yongjin, Eunjung Lee, Daeyoung Choi, Yongjae Lee, Wonjong Rhee

arXiv (Cornell University) · Published 23 May 2019 · DOI 10.48550/arxiv.1905.09680

Open PDFView at the publisherCite this paper

In brief

“DEEP-BO for Hyperparameter Optimization of Deep Networks” is a 2019 preprint by Hyunghun Cho and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2021 (1)
References
36
Authors
6

Abstract

The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation. The code used is made publicly available at https://github.com/snu-adsl/DEEP-BO.

Cite this paper

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

APA 7

Cho, H., Yongjin, K., Lee, E., Choi, D., Lee, Y., & Rhee, W. (2019). DEEP-BO for Hyperparameter Optimization of Deep Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.09680

MLA 9

Cho, Hyunghun, et al. “DEEP-BO for Hyperparameter Optimization of Deep Networks.” arXiv (Cornell University), 2019. https://doi.org/10.48550/arxiv.1905.09680.

Chicago

Cho, Hyunghun, Kim, Yongjin, Eunjung Lee, Daeyoung Choi, Yongjae Lee, and Wonjong Rhee. 2019. “DEEP-BO for Hyperparameter Optimization of Deep Networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.09680.

Harvard

Cho, H. et al. (2019) ‘DEEP-BO for Hyperparameter Optimization of Deep Networks’, arXiv (Cornell University). doi:10.48550/arxiv.1905.09680.

IEEE

H. Cho, K. Yongjin, E. Lee, D. Choi, Y. Lee, and W. Rhee, “DEEP-BO for Hyperparameter Optimization of Deep Networks,” arXiv (Cornell University), 2019, doi: 10.48550/arxiv.1905.09680.

BibTeX

@misc{cho2019deep,
  title     = {{DEEP-BO for Hyperparameter Optimization of Deep Networks}},
  author    = {Cho, Hyunghun and Yongjin, Kim, and Lee, Eunjung and Choi, Daeyoung and Lee, Yongjae and Rhee, Wonjong},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  doi       = {10.48550/arxiv.1905.09680},
  url       = {https://doi.org/10.48550/arxiv.1905.09680}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification

  • hyperparameter optimization
  • deep neural network
  • Bayesian optimization
  • early termination
  • learning curve
  • batch normalization
  • Hyperband

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?

Cho, H., Yongjin, K., Lee, E., Choi, D., Lee, Y., & Rhee, W. (2019). DEEP-BO for Hyperparameter Optimization of Deep Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.09680

How many times has this paper been cited?

2 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 PDF from this page.

Who wrote this paper?

Hyunghun Cho, Kim, Yongjin, Eunjung Lee, Daeyoung Choi, Yongjae Lee, Wonjong Rhee.

What is the DOI of this paper?

10.48550/arxiv.1905.09680, permanently at https://doi.org/10.48550/arxiv.1905.09680. Sign in and open it from this page.

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.