Preprint · 2021 · Open access
Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation
arXiv (Cornell University) · Published 17 June 2021 · DOI 10.48550/arxiv.2106.09179
In brief
“Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation” is a 2021 preprint by Yuxin Xiao and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 6 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 6
- Most cited in
- 2022 (2)
- References
- 49
- Authors
- 3
Abstract
With the surge in the number of hyperparameters and training times of modern machine learning models, hyperparameter tuning is becoming increasingly expensive. However, after assessing 40 tuning methods systematically, we find that each faces certain limitations. In particular, methods that speed up tuning via knowledge transfer typically require the final performance of hyperparameters and do not focus on low-fidelity information. As we demonstrate empirically, this common practice is suboptimal and can incur an unnecessary use of resources. It is more cost-efficient to instead leverage low-fidelity tuning observations to measure inter-task similarity and transfer knowledge from existing to new tasks accordingly. However, performing multi-fidelity tuning comes with its own challenges in the transfer setting: the noise in additional observations and the need for performance forecasting. Therefore, we propose and conduct a thorough analysis of a multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2). We further present an offline-computed 27-task hyperparameter recommendation (HyperRec) database to serve the community. Extensive experiments on HyperRec and other real-world databases illustrate the effectiveness of our AT2 method.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Xiao, Y., Xing, E. P., & Neiswanger, W. (2021). Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.09179
MLA 9
Xiao, Yuxin, et al. “Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2106.09179.
Chicago
Xiao, Yuxin, Eric P. Xing, and Willie Neiswanger. 2021. “Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.09179.
Harvard
Xiao, Y., Xing, E. P. and Neiswanger, W. (2021) ‘Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation’, arXiv (Cornell University). doi:10.48550/arxiv.2106.09179.
IEEE
Y. Xiao, E. P. Xing, and W. Neiswanger, “Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2106.09179.
BibTeX
@misc{xiao2021amortized,
title = {{Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation}},
author = {Xiao, Yuxin and Xing, Eric P. and Neiswanger, Willie},
howpublished = {arXiv (Cornell University)},
year = {2021},
doi = {10.48550/arxiv.2106.09179},
url = {https://doi.org/10.48550/arxiv.2106.09179}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2021 | 1 | |
| 2022 | 2 | |
| 2023 | 1 | |
| 2024 | 1 | |
| 2026 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- hyperparameter optimization
- multi-fidelity Bayesian optimization
- knowledge transfer
- performance prediction
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?
Xiao, Y., Xing, E. P., & Neiswanger, W. (2021). Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.09179
How many times has this paper been cited?
6 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?
Yuxin Xiao, Eric P. Xing, Willie Neiswanger.
What is the DOI of this paper?
10.48550/arxiv.2106.09179, permanently at https://doi.org/10.48550/arxiv.2106.09179. 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.