Papers › Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

5 Dec 2016NeurIPS 2017 12arXiv:1612.01474archive 2025-07-28

Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell

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.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 6 repositories linked to this paper: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 6 repositories, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

26 repositories listed; official and paper-mentioned ones first.

Glutamat42/epistemic_ensemble_toy_dataset mentioned on GitHubMITSyntology: not harvested report
JoonHyung-Park/DeepEnsemble mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Junghwan-brian/SDE-Net mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
Kyushik/Predictive-Uncertainty-Estimation-using-Deep-Ensemble mentioned on GitHubtfSyntology: not harvested report
StanfordASL/SCOD mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
arnavc1712/DeepEnsembles mentioned on GitHubSyntology: not harvested report
axelbrando/Mixture-Density-Networks-for-distribution-and-uncertainty-estimation mentioned on GitHubtfApache-2.0Syntology: not harvested report
cameronccohen/deep-ensembles mentioned on GitHubpytorchSyntology: not harvested report
cpark321/bayesian-neural-networks mentioned on GitHubpytorchSyntology: not harvested report
cpark321/uncertainty-deep-learning mentioned on GitHubpytorchSyntology: not harvested report
dougbrion/pytorch-deep-ensembles mentioned on GitHubpytorchMITSyntology: not harvested report
hayoung-kim/tf2-deep-ensemble-uncertainty mentioned on GitHubtfSyntology: not harvested report
hoidn/ptychopinn mentioned on GitHubtfGPL-3.0Syntology: not harvested report
huyng/incertae mentioned on GitHubtfSyntology: not harvested report
omegafragger/DDU mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Energy-based Out-of-distribution Detection (arXiv:2010.03759; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
pycroscopy/atomai mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Introduction to Variational Autoencoders (arXiv:1906.02691; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
stat-ml/dpp-dropout-uncertainty mentioned on GitHubpytorchSyntology: not harvested report
statsu1990/deep_ensembles mentioned on GitHubMITSyntology: not harvested report
tkerscher/blast mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tykurtz/tensorflow_models mentioned on GitHubtfSyntology: not harvested report
vvanirudh/deep-ensembles-uncertainty mentioned on GitHubtfGPL-3.0Syntology: not harvested report
xuyxu/Ensemble-Pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (arXiv:1802.10026; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
ENSTA-U2IS-AI/torch-uncertainty pytorchApache-2.0Syntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
github-jnauta/pytorch-pne pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lightning-uq-box/lightning-uq-box pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Uncertainty Sets for Image Classifiers using Conformal Prediction (arXiv:2009.14193; that paper's own run record: 26 ran (of which 1 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 13 where Syntology's instrument failed) · 37 unverified), ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference (arXiv:2211.11435; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified) and Variational Bayesian Last Layers (arXiv:2404.11599; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
mvaldenegro/keras-uncertainty tfLGPL-3.0Syntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
9ran
1unverified

Licence: 6 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

JoonHyung-Park/DeepEnsemble community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GaussianMLP complete_ver/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2bb0022c0652839d · report fixture: returned GaussianMLP · level recorded 2026-09-22
MLP in 375 papers complete_ver/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8f0ebe8c1a69cb4b · report fixture: returned MLP · level recorded 2026-09-22
Junghwan-brian/SDE-Net community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Diffusion in 21 papers model/SDENet.py ran no licence file found · pointer only · 59b274fed1c2f7d5 · report fixture: returned Diffusion · level recorded 2026-09-22
Drift model/SDENet.py ran no licence file found · pointer only · 9ceff01e171db846 · report fixture: returned Drift · level recorded 2026-09-22
SDENet model/SDENet.py unverified no licence file found · pointer only · 9c625ca32e821ccc · report
StanfordASL/SCOD community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Ensemble in 6 papers nn_ood/posteriors/ensemble.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · cfe90024d387377b · report fixture: returned Ensemble · level recorded 2026-09-22
tkerscher/blast community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
parse_sed blast/parser.py ran MIT (permissive) · a03d09d6f461b685 · report fixture: signature sed:str/0/str, sanitize:bool/0/bool, position:bool/0/bool · returned ndarray · level recorded 2026-09-26
ENSTA-U2IS-AI/torch-uncertainty community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
_DeepEnsembles src/torch_uncertainty/methods/deep_ensembles.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · b8e6a0ddc977191d · report fixture: returned _DeepEnsembles · level recorded 2026-09-22
_RegDeepEnsembles src/torch_uncertainty/methods/deep_ensembles.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 5425e2595166ea3a · report fixture: returned _RegDeepEnsembles · level recorded 2026-09-22
deep_ensembles src/torch_uncertainty/methods/deep_ensembles.py ran · our draft was wrong Apache-2.0 (permissive) · a76c86e0e721e4b2 · report fixture: signature core_models:list/1/callable, num_estimators:NoneType/0/?, task:str/0/str, probabilistic:NoneType/0/?, reset_model_parameters:bool/0/bool, store_on_cpu:bool/0/bool, ckpt_paths:NoneType/0/?, use_tu_ckpt_format:bool/0/bool · returned _DeepEnsembles · level recorded 2026-09-22
github-jnauta/pytorch-pne community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Model in 227 papers models/pnn.py ran no licence file found · pointer only · 1fbc81b2bd6ea48b · report fixture: returned Model · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for Deep Ensembles (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Deep Ensembles (graph method: Deep Ensembles). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. Ensemble entry · level 1 · ran · cfe90024d387377b

harvested Assembly for Deep Ensembles (graph method: Deep Ensembles). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. deep_ensembles entry · level 1 · ran · our draft was wrong · a76c86e0e721e4b2
  2. _DeepEnsembles model · level 1 · ran · b8e6a0ddc977191d
  3. _RegDeepEnsembles model · level 1 · ran · 5425e2595166ea3a

harvested Assembly for Deep Ensembles (graph method: Deep Ensembles). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. GaussianMLP entry · level 1 · ran · 2bb0022c0652839d
  2. MLP helper · level 1 · ran · 8f0ebe8c1a69cb4b

harvested Assembly for Deep Ensembles (graph method: Deep Ensembles). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. Model entry · level 1 · ran · 1fbc81b2bd6ea48b

harvested Assembly for Deep Ensembles (graph method: Deep Ensembles). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. SDENet entry · level 0 · unverified · 9c625ca32e821ccc
  2. Diffusion model · level 1 · ran · 59b274fed1c2f7d5
  3. Drift model · level 1 · ran · 9ceff01e171db846

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1612.01474") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationUncertainty Quantificationregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Deep Ensembles

Deep Ensembles

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections