Preprint · 2016 · Open access

Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell

arXiv (Cornell University) · Published 5 December 2016 · DOI 10.48550/arxiv.1612.01474

Open PDFView at the publisherCite this paper

In brief

“Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles” is a 2016 preprint by Balaji Lakshminarayanan and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 5,187 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
5,187
Most cited in
2021 (790)
References
60
Authors
3

Abstract

Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs, which learn a distribution over weights, are currently the state-of-the-art for estimating predictive uncertainty; however these require significant modifications to the training procedure and are computationally expensive compared to standard (non-Bayesian) NNs. We propose an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates. Through a series of experiments on classification and regression benchmarks, we demonstrate that our method produces well-calibrated uncertainty estimates which are as good or better than approximate Bayesian NNs. To assess robustness to dataset shift, we evaluate the predictive uncertainty on test examples from known and unknown distributions, and show that our method is able to express higher uncertainty on out-of-distribution examples. We demonstrate the scalability of our method by evaluating predictive uncertainty estimates on ImageNet.

Cite this paper

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

APA 7

Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016). Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1612.01474

MLA 9

Lakshminarayanan, Balaji, et al. “Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles.” arXiv (Cornell University), 2016. https://doi.org/10.48550/arxiv.1612.01474.

Chicago

Lakshminarayanan, Balaji, Alexander Pritzel, and Charles Blundell. 2016. “Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1612.01474.

Harvard

Lakshminarayanan, B., Pritzel, A. and Blundell, C. (2016) ‘Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles’, arXiv (Cornell University). doi:10.48550/arxiv.1612.01474.

IEEE

B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles,” arXiv (Cornell University), 2016, doi: 10.48550/arxiv.1612.01474.

BibTeX

@misc{lakshminarayanan2016simple,
  title     = {{Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles}},
  author    = {Lakshminarayanan, Balaji and Pritzel, Alexander and Blundell, Charles},
  howpublished = {arXiv (Cornell University)},
  year      = {2016},
  doi       = {10.48550/arxiv.1612.01474},
  url       = {https://doi.org/10.48550/arxiv.1612.01474}
}

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

Citations by year

YearCitationsShare of the best year
20171818
2018105105
2019254254
2020496496
2021790790
2022592592
2023749749
2024757757
2025644644
2026781781

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • predictive uncertainty estimation
  • ensemble deep learning
  • ensemble averaging
  • Bayesian neural networks
  • uncertainty calibration
  • out-of-distribution detection
  • distribution shift
  • scalability

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?

Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016). Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1612.01474

How many times has this paper been cited?

5,187 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?

Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell.

What is the DOI of this paper?

10.48550/arxiv.1612.01474, permanently at https://doi.org/10.48550/arxiv.1612.01474. 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.