Methods › General › Stochastic Optimization › Deep Ensembles
Deep Ensembles
Introduced by Balaji Lakshminarayanan et al. in Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 26 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:1612.01474, the paper the archive credits with this method.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- DEEP RANKING ENSEMBLES · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='DEEP RANKING ENSEMBLES') - Self-training Ensembles · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Self-training Ensembles') - diverse ensembles with different data augmentation · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='diverse ensembles with different data augmentation')
Origin paper of this answer, arXiv:1612.01474 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 11 harvested samples) · 6 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 177 · with a code link: 81 · where Syntology ran a sample: 28 (21 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (28 of 177 tagged: 21 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 177, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Uncertainty Quantification for Motor Imagery BCI -- Machine Learning vs. Deep Learning 10 Jul 2025 · 0 repositories · arXiv:2507.07511
-
Last Layer Empirical Bayes 21 May 2025 · 0 repositories · arXiv:2505.15888
-
Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles 19 May 2025 · 0 repositories · arXiv:2505.13585
-
Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles 16 May 2025 · 0 repositories · arXiv:2505.11671
-
Hesitation is defeat? Connecting Linguistic and Predictive Uncertainty 6 May 2025 · 0 repositories · arXiv:2505.03910
-
Evaluating Uncertainty in Deep Gaussian Processes 24 Apr 2025 · 1 repository · arXiv:2504.17719
-
Efficient Epistemic Uncertainty Estimation in Cerebrovascular Segmentation 28 Mar 2025 · 0 repositories · arXiv:2503.22271
-
On Local Posterior Structure in Deep Ensembles 17 Mar 2025 · 1 repository · arXiv:2503.13296
-
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model 14 Mar 2025 · 0 repositories · arXiv:2503.11339
-
OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction 13 Mar 2025 · 1 repository · arXiv:2503.10605
-
Improving Deep Ensembles by Estimating Confusion Matrices 10 Mar 2025 · 0 repositories · arXiv:2503.07119
-
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE 24 Feb 2025 · 0 repositories · arXiv:2502.17391Syntology 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localization 3 Feb 2025 · 1 repository · arXiv:2502.01035Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)
-
Deep Ensembles Secretly Perform Empirical Bayes 29 Jan 2025 · 0 repositories · arXiv:2501.17917
-
HopCast: Calibration of Autoregressive Dynamics Models 27 Jan 2025 · 0 repositories · arXiv:2501.16587
-
Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles 20 Dec 2024 · 0 repositories · arXiv:2412.15758
-
Uncertainty separation via ensemble quantile regression 18 Dec 2024 · 0 repositories · arXiv:2412.13738
-
Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling 11 Dec 2024 · 0 repositories · arXiv:2412.08776
-
Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification 26 Nov 2024 · 0 repositories · arXiv:2411.17571
-
DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methods 13 Nov 2024 · 1 repository · arXiv:2411.08587
-
Stein Variational Newton Neural Network Ensembles 4 Nov 2024 · 1 repository · arXiv:2411.01887
-
Theoretical Limitations of Ensembles in the Age of Overparameterization 21 Oct 2024 · 0 repositories · arXiv:2410.16201
-
The Disparate Benefits of Deep Ensembles 17 Oct 2024 · 1 repository · arXiv:2410.13831Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation 11 Oct 2024 · 0 repositories · arXiv:2410.08687
-
Boosting Deep Ensembles with Learning Rate Tuning 10 Oct 2024 · 0 repositories · arXiv:2410.07564
-
Achieving Generalization in Orchestrating GNSS Interference Monitoring Stations Through Pseudo-Labeling 3 Oct 2024 · 0 repositories · arXiv:2410.14686
-
Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection 26 Sep 2024 · 1 repository · arXiv:2409.17485
-
Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning 16 Sep 2024 · 0 repositories · arXiv:2409.10655
-
Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning 26 Jul 2024 · 0 repositories · arXiv:2407.19119
-
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance 17 Jul 2024 · 0 repositories · arXiv:2407.12996
-
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss 16 Jul 2024 · 1 repository · arXiv:2407.12211
-
Uncertainty modeling for fine-tuned implicit functions 17 Jun 2024 · 0 repositories · arXiv:2406.12082
-
On Uniform, Bayesian, and PAC-Bayesian Deep Ensembles 8 Jun 2024 · 0 repositories · arXiv:2406.05469
-
Scalable Bayesian Learning with posteriors 31 May 2024 · 1 repository · arXiv:2406.00104
-
A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation 27 May 2024 · 0 repositories · arXiv:2405.17097
-
Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification 23 May 2024 · 0 repositories · arXiv:2405.15047
-
Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems 9 May 2024 · 1 repository
-
Predicting Safety Misbehaviours in Autonomous Driving Systems using Uncertainty Quantification 29 Apr 2024 · 1 repository · arXiv:2404.18573
-
Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks 3 Apr 2024 · 0 repositories · arXiv:2404.03099
-
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting 26 Mar 2024 · 1 repository · arXiv:2403.17678
-
Diversity-Aware Agnostic Ensemble of Sharpness Minimizers 19 Mar 2024 · 0 repositories · arXiv:2403.13204
-
Uncertainty Quantification for cross-subject Motor Imagery classification 14 Mar 2024 · 1 repository · arXiv:2403.09228
-
Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation 12 Mar 2024 · 0 repositories · arXiv:2403.07741
-
Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shifts 7 Mar 2024 · 1 repository · arXiv:2403.05600
-
Emergent Equivariance in Deep Ensembles 5 Mar 2024 · 0 repositories · arXiv:2403.03103
-
Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation 4 Mar 2024 · 0 repositories · arXiv:2403.02311
-
Quantifying neural network uncertainty under volatility clustering 22 Feb 2024 · 0 repositories · arXiv:2402.14476
-
The Importance of Architecture Choice in Deep Learning for Climate Applications 21 Feb 2024 · 0 repositories · arXiv:2402.13979
-
How Good is a Single Basin? 5 Feb 2024 · 0 repositories · arXiv:2402.03187
-
CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks 10 Jan 2024 · 0 repositories · arXiv:2401.05043
-
Packed-Ensemble Surrogate Models for Fluid Flow Estimation Arround Airfoil Geometries 20 Dec 2023 · 0 repositories · arXiv:2312.13403
-
Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series 3 Dec 2023 · 0 repositories · arXiv:2312.01294
-
Hierarchical Pruning of Deep Ensembles with Focal Diversity 17 Nov 2023 · 1 repository · arXiv:2311.10293
-
Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific applications 8 Nov 2023 · 0 repositories · arXiv:2311.04457
-
Sensitivity-Aware Amortized Bayesian Inference 17 Oct 2023 · 1 repository · arXiv:2310.11122Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data 4 Oct 2023 · 0 repositories · arXiv:2310.02885
-
Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness 3 Oct 2023 · 1 repository · arXiv:2310.02237
-
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection 26 Sep 2023 · 1 repository · arXiv:2309.14976Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift 21 Sep 2023 · 1 repository
-
Explaining Predictive Uncertainty with Information Theoretic Shapley Values 21 Sep 2023 · 1 repository
-
Quantification of Uncertainty with Adversarial Models 21 Sep 2023 · 1 repository
-
You can have your ensemble and run it too -- Deep Ensembles Spread Over Time 20 Sep 2023 · 0 repositories · arXiv:2309.11333
-
Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learning 28 Aug 2023 · 0 repositories · arXiv:2308.14705
-
Comparing the quality of neural network uncertainty estimates for classification problems 11 Aug 2023 · 0 repositories · arXiv:2308.05903
-
Traversing Between Modes in Function Space for Fast Ensembling 20 Jun 2023 · 1 repository · arXiv:2306.11304Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
A Study of Bayesian Neural Network Surrogates for Bayesian Optimization 31 May 2023 · 2 repositories · arXiv:2305.20028
-
Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertainty 26 May 2023 · 0 repositories · arXiv:2305.16620
-
A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods 24 May 2023 · 0 repositories · arXiv:2305.15027
-
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties 17 May 2023 · 0 repositories · arXiv:2305.10384
-
Synthetic data, real errors: how (not) to publish and use synthetic data 16 May 2023 · 1 repository · arXiv:2305.09235Syntology official (archive's flag): 14 ran · 14 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 8 unverified (of 22 harvested samples) · 22 pointer-only (licence)
-
Integrating Uncertainty into Neural Network-based Speech Enhancement 15 May 2023 · 1 repository · arXiv:2305.08744
-
Deep Ensembles to Improve Uncertainty Quantification of Statistical Downscaling Models under Climate Change Conditions 27 Apr 2023 · 0 repositories · arXiv:2305.00975
-
Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification 8 Apr 2023 · 0 repositories · arXiv:2304.04042
-
EPiC: Ensemble of Partial Point Clouds for Robust Classification 20 Mar 2023 · 1 repository · arXiv:2303.11419
-
Simple and Efficient Confidence Score for Grading Whole Slide Images 8 Mar 2023 · 0 repositories · arXiv:2303.04604
-
CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19 17 Feb 2023 · 0 repositories · arXiv:2302.09004
-
Optimal Training of Mean Variance Estimation Neural Networks 17 Feb 2023 · 1 repository · arXiv:2302.08875
-
Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts 13 Feb 2023 · 1 repository · arXiv:2302.06495Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples)
-
A Benchmark on Uncertainty Quantification for Deep Learning Prognostics 9 Feb 2023 · 1 repository · arXiv:2302.04730
-
Pathologies of Predictive Diversity in Deep Ensembles 1 Feb 2023 · 0 repositories · arXiv:2302.00704
-
Joint Training of Deep Ensembles Fails Due to Learner Collusion 26 Jan 2023 · 1 repository · arXiv:2301.11323
-
Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise 3 Jan 2023 · 0 repositories · arXiv:2301.01054
-
Deep Deterministic Uncertainty: A New Simple Baseline 1 Jan 2023 · 0 repositories
-
Boosting Out-of-Distribution Detection with Multiple Pre-trained Models 24 Dec 2022 · 1 repository · arXiv:2212.12720
-
An Ensemble-Based Deep Framework for Estimating Thermo-Chemical State Variables from Flamelet Generated Manifolds 25 Nov 2022 · 0 repositories · arXiv:2211.14098
-
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference 21 Nov 2022 · 2 repositories · arXiv:2211.11435Syntology official (archive's flag): 2 ran · 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 (of 6 harvested samples)
-
Fast Uncertainty Estimates in Deep Learning Interatomic Potentials 17 Nov 2022 · 1 repository · arXiv:2211.09866
-
A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation 11 Nov 2022 · 0 repositories · arXiv:2211.06241
-
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel 18 Oct 2022 · 0 repositories · arXiv:2210.09818
-
Packed-Ensembles for Efficient Uncertainty Estimation 17 Oct 2022 · 1 repository · arXiv:2210.09184Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
Layer Ensembles 10 Oct 2022 · 2 repositories · arXiv:2210.04882
-
How to Enable Uncertainty Estimation in Proximal Policy Optimization 7 Oct 2022 · 0 repositories · arXiv:2210.03649
-
Uncertainty-Aware Lidar Place Recognition in Novel Environments 4 Oct 2022 · 1 repository · arXiv:2210.01361
-
Deep Convolutional Architectures for Extrapolative Forecast in Time-dependent Flow Problems 18 Sep 2022 · 0 repositories · arXiv:2209.09651
-
Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training 5 Sep 2022 · 0 repositories · arXiv:2209.03148
-
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation 22 Jul 2022 · 0 repositories · arXiv:2207.11211
-
Latent Discriminant deterministic Uncertainty 20 Jul 2022 · 1 repository · arXiv:2207.10130Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection 15 Jul 2022 · 1 repository · arXiv:2207.07517Syntology official (archive's flag): 8 ran · 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) · 1 unverified (of 9 harvested samples) · 2 pointer-only (licence)
-
Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models 27 Jun 2022 · 0 repositories · arXiv:2206.14615
-
Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift 17 Jun 2022 · 0 repositories · arXiv:2206.08640
Tasks archive 2025-07-28
20 shown of 154 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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