Preprint · 2022 · Open access
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
arXiv (Cornell University) · Published 1 May 2022 · DOI 10.48550/arxiv.2205.00403
In brief
“A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness” is a 2022 preprint by Jeremiah Zhe Liu and 9 co-authors, published in arXiv (Cornell University). OpenAlex counts 65 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 65
- Most cited in
- 2025 (19)
- References
- 116
- Authors
- 10
Abstract
Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. Code is open-sourced at https://github.com/google/uncertainty-baselines
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Liu, J. Z., Padhy, S., Ren, J., Zi, L., Wen, Y., Jerfel, G., Nado, Z., Snoek, J., Tran, D., & Lakshminarayanan, B. (2022). A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.00403
MLA 9
Liu, Jeremiah Zhe, et al. “A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2205.00403.
Chicago
Liu, Jeremiah Zhe, Shreyas Padhy, Jie Ren, Lin Zi, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, and Balaji Lakshminarayanan. 2022. “A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.00403.
Harvard
Liu, J. Z. et al. (2022) ‘A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness’, arXiv (Cornell University). doi:10.48550/arxiv.2205.00403.
IEEE
J. Z. Liu et al., “A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2205.00403.
BibTeX
@misc{liu2022simple,
title = {{A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness}},
author = {Liu, Jeremiah Zhe and Padhy, Shreyas and Ren, Jie and Zi, Lin and Wen, Yeming and Jerfel, Ghassen and Nado, Zack and Snoek, Jasper and Tran, Dustin and Lakshminarayanan, Balaji},
howpublished = {arXiv (Cornell University)},
year = {2022},
doi = {10.48550/arxiv.2205.00403},
url = {https://doi.org/10.48550/arxiv.2205.00403}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 5 | |
| 2023 | 15 | |
| 2024 | 15 | |
| 2025 | 19 | |
| 2026 | 11 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- spectral normalization
- out-of-distribution detection
- calibration
- probabilistic deep learning
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?
Liu, J. Z., Padhy, S., Ren, J., Zi, L., Wen, Y., Jerfel, G., Nado, Z., Snoek, J., Tran, D., & Lakshminarayanan, B. (2022). A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.00403
How many times has this paper been cited?
65 times, according to OpenAlex on 22 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?
Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Lin Zi, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan.
What is the DOI of this paper?
10.48550/arxiv.2205.00403, permanently at https://doi.org/10.48550/arxiv.2205.00403. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 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.