{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/deep-ensembles","slug":"deep-ensembles","name":"Deep Ensembles","full_name":"Deep Ensembles","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","paper":"/paper/simple-and-scalable-predictive-uncertainty","first_author":"Balaji Lakshminarayanan","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/simple-and-scalable-predictive-uncertainty"},"source":{"url":"http://arxiv.org/abs/1612.01474v3","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":177,"archive_num_papers":177,"papers_newest_first":[{"paper":null,"slug":"uncertainty-quantification-for-motor-imagery","title":"Uncertainty Quantification for Motor Imagery BCI -- Machine Learning vs. Deep Learning","date":"2025-07-10","arxiv_id":"2507.07511","n_code_links":0,"syntology":null},{"paper":null,"slug":"last-layer-empirical-bayes","title":"Last Layer Empirical Bayes","date":"2025-05-21","arxiv_id":"2505.15888","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-bayesian-monte-carlo-fast","title":"Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles","date":"2025-05-19","arxiv_id":"2505.13585","n_code_links":0,"syntology":null},{"paper":null,"slug":"humble-your-overconfident-networks-unlearning","title":"Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles","date":"2025-05-16","arxiv_id":"2505.11671","n_code_links":0,"syntology":null},{"paper":null,"slug":"hesitation-is-defeat-connecting-linguistic","title":"Hesitation is defeat? Connecting Linguistic and Predictive Uncertainty","date":"2025-05-06","arxiv_id":"2505.03910","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-uncertainty-in-deep-gaussian","slug":"evaluating-uncertainty-in-deep-gaussian","title":"Evaluating Uncertainty in Deep Gaussian Processes","date":"2025-04-24","arxiv_id":"2504.17719","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-epistemic-uncertainty-estimation-in","title":"Efficient Epistemic Uncertainty Estimation in Cerebrovascular Segmentation","date":"2025-03-28","arxiv_id":"2503.22271","n_code_links":0,"syntology":null},{"paper":"/paper/on-local-posterior-structure-in-deep","slug":"on-local-posterior-structure-in-deep","title":"On Local Posterior Structure in Deep Ensembles","date":"2025-03-17","arxiv_id":"2503.13296","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-similarity-distillation-ensemble","title":"Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model","date":"2025-03-14","arxiv_id":"2503.11339","n_code_links":0,"syntology":null},{"paper":"/paper/occuq-exploring-efficient-uncertainty","slug":"occuq-exploring-efficient-uncertainty","title":"OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction","date":"2025-03-13","arxiv_id":"2503.10605","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-deep-ensembles-by-estimating","title":"Improving Deep Ensembles by Estimating Confusion Matrices","date":"2025-03-10","arxiv_id":"2503.07119","n_code_links":0,"syntology":null},{"paper":"/paper/the-empirical-impact-of-reducing-symmetries","slug":"the-empirical-impact-of-reducing-symmetries","title":"The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE","date":"2025-02-24","arxiv_id":"2502.17391","n_code_links":0,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"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","official":null}},{"paper":"/paper/uasthn-uncertainty-aware-deep-homography","slug":"uasthn-uncertainty-aware-deep-homography","title":"UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localization","date":"2025-02-03","arxiv_id":"2502.01035","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["arplaboratory/UASTHN"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-ensembles-secretly-perform-empirical","title":"Deep Ensembles Secretly Perform Empirical Bayes","date":"2025-01-29","arxiv_id":"2501.17917","n_code_links":0,"syntology":null},{"paper":null,"slug":"hopcast-calibration-of-autoregressive","title":"HopCast: Calibration of Autoregressive Dynamics Models","date":"2025-01-27","arxiv_id":"2501.16587","n_code_links":0,"syntology":null},{"paper":null,"slug":"function-space-diversity-for-uncertainty","title":"Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles","date":"2024-12-20","arxiv_id":"2412.15758","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-separation-via-ensemble-quantile","title":"Uncertainty separation via ensemble quantile regression","date":"2024-12-18","arxiv_id":"2412.13738","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-optimized-deep-ensemble-for","title":"Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling","date":"2024-12-11","arxiv_id":"2412.08776","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-quantification-for-white-matter","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","date":"2024-11-26","arxiv_id":"2411.17571","n_code_links":0,"syntology":null},{"paper":"/paper/deepuq-assessing-the-aleatoric-uncertainties","slug":"deepuq-assessing-the-aleatoric-uncertainties","title":"DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methods","date":"2024-11-13","arxiv_id":"2411.08587","n_code_links":1,"syntology":null},{"paper":"/paper/stein-variational-newton-neural-network","slug":"stein-variational-newton-neural-network","title":"Stein Variational Newton Neural Network Ensembles","date":"2024-11-04","arxiv_id":"2411.01887","n_code_links":1,"syntology":null},{"paper":null,"slug":"theoretical-limitations-of-ensembles-in-the","title":"Theoretical Limitations of Ensembles in the Age of Overparameterization","date":"2024-10-21","arxiv_id":"2410.16201","n_code_links":0,"syntology":null},{"paper":"/paper/the-disparate-benefits-of-deep-ensembles","slug":"the-disparate-benefits-of-deep-ensembles","title":"The Disparate Benefits of Deep Ensembles","date":"2024-10-17","arxiv_id":"2410.13831","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"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","official":{"repos":["ml-jku/disparate-benefits"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uncertainty-estimation-and-out-of-1","title":"Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation","date":"2024-10-11","arxiv_id":"2410.08687","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-deep-ensembles-with-learning-rate","title":"Boosting Deep Ensembles with Learning Rate Tuning","date":"2024-10-10","arxiv_id":"2410.07564","n_code_links":0,"syntology":null},{"paper":null,"slug":"achieving-generalization-in-orchestrating","title":"Achieving Generalization in Orchestrating GNSS Interference Monitoring Stations Through Pseudo-Labeling","date":"2024-10-03","arxiv_id":"2410.14686","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-deep-ensemble-uncertainty-for","slug":"revisiting-deep-ensemble-uncertainty-for","title":"Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection","date":"2024-09-26","arxiv_id":"2409.17485","n_code_links":1,"syntology":null},{"paper":null,"slug":"disentangling-uncertainty-for-safe-social","title":"Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning","date":"2024-09-16","arxiv_id":"2409.10655","n_code_links":0,"syntology":null},{"paper":null,"slug":"accuracy-privacy-trade-off-in-the-mitigation","title":"Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning","date":"2024-07-26","arxiv_id":"2407.19119","n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-diversity-tradeoff-improving-flat","title":"Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance","date":"2024-07-17","arxiv_id":"2407.12996","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-calibration-of-epistemic-uncertainty","slug":"on-the-calibration-of-epistemic-uncertainty","title":"On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss","date":"2024-07-16","arxiv_id":"2407.12211","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-modeling-for-fine-tuned-implicit","title":"Uncertainty modeling for fine-tuned implicit functions","date":"2024-06-17","arxiv_id":"2406.12082","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-vs-pac-bayesian-deep-neural-network","title":"On Uniform, Bayesian, and PAC-Bayesian Deep Ensembles","date":"2024-06-08","arxiv_id":"2406.05469","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-bayesian-learning-with-posteriors","slug":"scalable-bayesian-learning-with-posteriors","title":"Scalable Bayesian Learning with posteriors","date":"2024-05-31","arxiv_id":"2406.00104","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-multi-task-uncertainties-in","title":"A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation","date":"2024-05-27","arxiv_id":"2405.17097","n_code_links":0,"syntology":null},{"paper":null,"slug":"credal-wrapper-of-model-averaging-for","title":"Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification","date":"2024-05-23","arxiv_id":"2405.15047","n_code_links":0,"syntology":null},{"paper":"/paper/audio-visual-speech-recognition-based-on","slug":"audio-visual-speech-recognition-based-on","title":"Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems","date":"2024-05-09","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/predicting-safety-misbehaviours-in-autonomous","slug":"predicting-safety-misbehaviours-in-autonomous","title":"Predicting Safety Misbehaviours in Autonomous Driving Systems using Uncertainty Quantification","date":"2024-04-29","arxiv_id":"2404.18573","n_code_links":1,"syntology":null},{"paper":null,"slug":"composite-bayesian-optimization-in-function","title":"Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks","date":"2024-04-03","arxiv_id":"2404.03099","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-light-transformer-ensembles-for","slug":"hierarchical-light-transformer-ensembles-for","title":"Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting","date":"2024-03-26","arxiv_id":"2403.17678","n_code_links":1,"syntology":null},{"paper":null,"slug":"diversity-aware-agnostic-ensemble-of","title":"Diversity-Aware Agnostic Ensemble of Sharpness Minimizers","date":"2024-03-19","arxiv_id":"2403.13204","n_code_links":0,"syntology":null},{"paper":"/paper/uncertainty-quantification-for-cross-subject","slug":"uncertainty-quantification-for-cross-subject","title":"Uncertainty Quantification for cross-subject Motor Imagery classification","date":"2024-03-14","arxiv_id":"2403.09228","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-quantification-with-deep","title":"Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation","date":"2024-03-12","arxiv_id":"2403.07741","n_code_links":0,"syntology":null},{"paper":"/paper/density-regression-efficient-and-distance","slug":"density-regression-efficient-and-distance","title":"Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shifts","date":"2024-03-07","arxiv_id":"2403.05600","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergent-equivariance-in-deep-ensembles","title":"Emergent Equivariance in Deep Ensembles","date":"2024-03-05","arxiv_id":"2403.03103","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-uncertainty-estimation-by","title":"Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation","date":"2024-03-04","arxiv_id":"2403.02311","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-neural-network-uncertainty-under","title":"Quantifying neural network uncertainty under volatility clustering","date":"2024-02-22","arxiv_id":"2402.14476","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-importance-of-architecture-choice-in-deep","title":"The Importance of Architecture Choice in Deep Learning for Climate Applications","date":"2024-02-21","arxiv_id":"2402.13979","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-a-single-basin","title":"How Good is a Single Basin?","date":"2024-02-05","arxiv_id":"2402.03187","n_code_links":0,"syntology":null},{"paper":null,"slug":"creinns-credal-set-interval-neural-networks","title":"CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks","date":"2024-01-10","arxiv_id":"2401.05043","n_code_links":0,"syntology":null},{"paper":null,"slug":"packed-ensemble-surrogate-models-for-fluid","title":"Packed-Ensemble Surrogate Models for Fluid Flow Estimation Arround Airfoil Geometries","date":"2023-12-20","arxiv_id":"2312.13403","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-ensembles-meets-quantile-regression","title":"Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series","date":"2023-12-03","arxiv_id":"2312.01294","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-pruning-of-deep-ensembles-with","slug":"hierarchical-pruning-of-deep-ensembles-with","title":"Hierarchical Pruning of Deep Ensembles with Focal Diversity","date":"2023-11-17","arxiv_id":"2311.10293","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-uncertainty-quantification","title":"Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific applications","date":"2023-11-08","arxiv_id":"2311.04457","n_code_links":0,"syntology":null},{"paper":"/paper/sensitivity-aware-amortized-bayesian","slug":"sensitivity-aware-amortized-bayesian","title":"Sensitivity-Aware Amortized Bayesian Inference","date":"2023-10-17","arxiv_id":"2310.11122","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"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","official":{"repos":["bayesflow-org/SA-ABI"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"something-for-almost-nothing-improving-deep","title":"Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data","date":"2023-10-04","arxiv_id":"2310.02885","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-model-learning-heterogeneity-for","slug":"exploring-model-learning-heterogeneity-for","title":"Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness","date":"2023-10-03","arxiv_id":"2310.02237","n_code_links":1,"syntology":null},{"paper":"/paper/mocae-mixture-of-calibrated-experts","slug":"mocae-mixture-of-calibrated-experts","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","date":"2023-09-26","arxiv_id":"2309.14976","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"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","official":{"repos":["fiveai/MoCaE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-deep-ensembles-a-large-scale","slug":"beyond-deep-ensembles-a-large-scale","title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/explaining-predictive-uncertainty-with","slug":"explaining-predictive-uncertainty-with","title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/quantification-of-uncertainty-with","slug":"quantification-of-uncertainty-with","title":"Quantification of Uncertainty with Adversarial Models","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"you-can-have-your-ensemble-and-run-it-too","title":"You can have your ensemble and run it too -- Deep Ensembles Spread Over Time","date":"2023-09-20","arxiv_id":"2309.11333","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversified-ensemble-of-independent-sub","title":"Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learning","date":"2023-08-28","arxiv_id":"2308.14705","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-the-quality-of-neural-network","title":"Comparing the quality of neural network uncertainty estimates for classification problems","date":"2023-08-11","arxiv_id":"2308.05903","n_code_links":0,"syntology":null},{"paper":"/paper/traversing-between-modes-in-function-space","slug":"traversing-between-modes-in-function-space","title":"Traversing Between Modes in Function Space for Fast Ensembling","date":"2023-06-20","arxiv_id":"2306.11304","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["yuneg11/Bridge-Network"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-study-of-bayesian-neural-network-surrogates","slug":"a-study-of-bayesian-neural-network-surrogates","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","date":"2023-05-31","arxiv_id":"2305.20028","n_code_links":2,"syntology":null},{"paper":null,"slug":"pedestrian-trajectory-forecasting-using-deep","title":"Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertainty","date":"2023-05-26","arxiv_id":"2305.16620","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-rigorous-link-between-deep-ensembles-and","title":"A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods","date":"2023-05-24","arxiv_id":"2305.15027","n_code_links":0,"syntology":null},{"paper":null,"slug":"logit-based-ensemble-distribution","title":"Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties","date":"2023-05-17","arxiv_id":"2305.10384","n_code_links":0,"syntology":null},{"paper":"/paper/synthetic-data-real-errors-how-not-to-publish","slug":"synthetic-data-real-errors-how-not-to-publish","title":"Synthetic data, real errors: how (not) to publish and use synthetic data","date":"2023-05-16","arxiv_id":"2305.09235","n_code_links":1,"syntology":{"ran":14,"of":22,"n_ran_checked":3,"n_instrument":11,"unverified":8,"pointer_only":22,"phrase":"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","official":{"repos":["bvanbreugel/deep_generative_ensemble"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/integrating-uncertainty-into-neural-network","slug":"integrating-uncertainty-into-neural-network","title":"Integrating Uncertainty into Neural Network-based Speech Enhancement","date":"2023-05-15","arxiv_id":"2305.08744","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-ensembles-to-improve-uncertainty","title":"Deep Ensembles to Improve Uncertainty Quantification of Statistical Downscaling Models under Climate Change Conditions","date":"2023-04-27","arxiv_id":"2305.00975","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-anti-regularized-ensembles-provide","title":"Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification","date":"2023-04-08","arxiv_id":"2304.04042","n_code_links":0,"syntology":null},{"paper":"/paper/epic-ensemble-of-partial-point-clouds-for","slug":"epic-ensemble-of-partial-point-clouds-for","title":"EPiC: Ensemble of Partial Point Clouds for Robust Classification","date":"2023-03-20","arxiv_id":"2303.11419","n_code_links":1,"syntology":null},{"paper":null,"slug":"simple-and-efficient-confidence-score-for","title":"Simple and Efficient Confidence Score for Grading Whole Slide Images","date":"2023-03-08","arxiv_id":"2303.04604","n_code_links":0,"syntology":null},{"paper":"/paper/covidexpert-a-triplet-siamese-neural-network","slug":"covidexpert-a-triplet-siamese-neural-network","title":"CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19","date":"2023-02-17","arxiv_id":"2302.09004","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-training-of-mean-variance-estimation","slug":"optimal-training-of-mean-variance-estimation","title":"Optimal Training of Mean Variance Estimation Neural Networks","date":"2023-02-17","arxiv_id":"2302.08875","n_code_links":1,"syntology":null},{"paper":"/paper/density-softmax-scalable-and-distance-aware","slug":"density-softmax-scalable-and-distance-aware","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","date":"2023-02-13","arxiv_id":"2302.06495","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"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","official":{"repos":["angie-lab-jhu/density_softmax"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-benchmark-on-uncertainty-quantification-for","slug":"a-benchmark-on-uncertainty-quantification-for","title":"A Benchmark on Uncertainty Quantification for Deep Learning Prognostics","date":"2023-02-09","arxiv_id":"2302.04730","n_code_links":1,"syntology":null},{"paper":null,"slug":"pathologies-of-predictive-diversity-in-deep","title":"Pathologies of Predictive Diversity in Deep Ensembles","date":"2023-02-01","arxiv_id":"2302.00704","n_code_links":0,"syntology":null},{"paper":"/paper/joint-training-of-deep-ensembles-fails-due-to","slug":"joint-training-of-deep-ensembles-fails-due-to","title":"Joint Training of Deep Ensembles Fails Due to Learner Collusion","date":"2023-01-26","arxiv_id":"2301.11323","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-common-uncertainty-estimation","title":"Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise","date":"2023-01-03","arxiv_id":"2301.01054","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-deterministic-uncertainty-a-new-simple","title":"Deep Deterministic Uncertainty: A New Simple Baseline","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/boosting-out-of-distribution-detection-with-1","slug":"boosting-out-of-distribution-detection-with-1","title":"Boosting Out-of-Distribution Detection with Multiple Pre-trained Models","date":"2022-12-24","arxiv_id":"2212.12720","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-ensemble-based-deep-framework-for","title":"An Ensemble-Based Deep Framework for Estimating Thermo-Chemical State Variables from Flamelet Generated Manifolds","date":"2022-11-25","arxiv_id":"2211.14098","n_code_links":0,"syntology":null},{"paper":"/paper/zigzag-universal-sampling-free-uncertainty","slug":"zigzag-universal-sampling-free-uncertainty","title":"ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference","date":"2022-11-21","arxiv_id":"2211.11435","n_code_links":2,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"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","official":{"repos":["cvlab-epfl/zigzag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-uncertainty-estimates-in-deep-learning","slug":"fast-uncertainty-estimates-in-deep-learning","title":"Fast Uncertainty Estimates in Deep Learning Interatomic Potentials","date":"2022-11-17","arxiv_id":"2211.09866","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-benchmark-for-out-of-distribution-detection","title":"A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation","date":"2022-11-11","arxiv_id":"2211.06241","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-the-predictive-variance-of-deep","title":"Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel","date":"2022-10-18","arxiv_id":"2210.09818","n_code_links":0,"syntology":null},{"paper":"/paper/packed-ensembles-for-efficient-uncertainty","slug":"packed-ensembles-for-efficient-uncertainty","title":"Packed-Ensembles for Efficient Uncertainty Estimation","date":"2022-10-17","arxiv_id":"2210.09184","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"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","official":{"repos":["ENSTA-U2IS-AI/torch-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/layer-ensembles","slug":"layer-ensembles","title":"Layer Ensembles","date":"2022-10-10","arxiv_id":"2210.04882","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-to-enable-uncertainty-estimation-in","title":"How to Enable Uncertainty Estimation in Proximal Policy Optimization","date":"2022-10-07","arxiv_id":"2210.03649","n_code_links":0,"syntology":null},{"paper":"/paper/uncertainty-aware-lidar-place-recognition-in","slug":"uncertainty-aware-lidar-place-recognition-in","title":"Uncertainty-Aware Lidar Place Recognition in Novel Environments","date":"2022-10-04","arxiv_id":"2210.01361","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-convolutional-architectures-for","title":"Deep Convolutional Architectures for Extrapolative Forecast in Time-dependent Flow Problems","date":"2022-09-18","arxiv_id":"2209.09651","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-out-of-distribution-detection-via","title":"Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training","date":"2022-09-05","arxiv_id":"2209.03148","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-predictive-performance-and","title":"Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation","date":"2022-07-22","arxiv_id":"2207.11211","n_code_links":0,"syntology":null},{"paper":"/paper/latent-discriminant-deterministic-uncertainty","slug":"latent-discriminant-deterministic-uncertainty","title":"Latent Discriminant deterministic Uncertainty","date":"2022-07-20","arxiv_id":"2207.10130","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"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","official":{"repos":["ensta-u2is/ldu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-usefulness-of-deep-ensemble-diversity","slug":"on-the-usefulness-of-deep-ensemble-diversity","title":"On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection","date":"2022-07-15","arxiv_id":"2207.07517","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"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","official":{"repos":["guoxoug/ens-div-ood-detect"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"quantification-of-deep-neural-network","title":"Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models","date":"2022-06-27","arxiv_id":"2206.14615","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-aware-evaluation-of-time-series","title":"Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift","date":"2022-06-17","arxiv_id":"2206.08640","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":177,"with_a_code_link":81,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":177,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":28,"papers_where_code_ran_first_page":"/method/deep-ensembles/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/deep-ensembles/papers/2","json":"/method/deep-ensembles/papers/2.json","rows":77},{"order":"ran","page":1,"of":1,"url":"/method/deep-ensembles/papers/ran/1","json":"/method/deep-ensembles/papers/ran/1.json","rows":28}],"tasks":[{"task":"/task/uncertainty-quantification","name":"Uncertainty Quantification","papers":62},{"task":"/task/diversity","name":"Diversity","papers":28},{"task":"/task/out-of-distribution-detection","name":"Out-of-Distribution Detection","papers":22},{"task":"/task/image-classification","name":"Image Classification","papers":16},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":16},{"task":"/task/deep-learning","name":"Deep Learning","papers":11},{"task":"/task/ood-detection","name":"Out of Distribution (OOD) Detection","papers":11},{"task":"/task/variational-inference","name":"Variational Inference","papers":11},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":10},{"task":"/task/decision-making","name":"Decision Making","papers":10},{"task":"/task/regression-1","name":"regression","papers":10},{"task":"/task/segmentation","name":"Segmentation","papers":9},{"task":"/task/image-classification","name":"image-classification","papers":9},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":8},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":7},{"task":"/task/active-learning","name":"Active Learning","papers":6},{"task":"/task/classification-1","name":"Classification","papers":6},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":6},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":5},{"task":"/task/time-series-1","name":"Time Series","papers":5}],"tasks_shown":20,"n_tasks":154,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":1},{"year":"2018","papers":2},{"year":"2019","papers":3},{"year":"2020","papers":22},{"year":"2021","papers":34},{"year":"2022","papers":31},{"year":"2023","papers":33},{"year":"2024","papers":35},{"year":"2025","papers":15}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deep-ensembles"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Deep%20Ensembles","read_at":"2026-10-05T00:54:35+00:00","query":"Deep Ensembles","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"Deep Ensembles","origin_arxiv_id":"1612.01474"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"1612.01474","repositories":{"listed":5,"in_graph":26,"list_truncated":true,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":3,"served":{"arxiv_id":"1612.01474","citations":8409},"leading_other_bearer":{"arxiv_id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","citations":787,"named_by":["title_prefix"],"bearer_name":"Deep Ensembles: A Loss Landscape Perspective","ask_with":"have('1912.02757')"},"n_other_bearers_listed":2,"note":"2 other thing(s) here are also called 'Deep Ensembles', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[{"name":"DEEP RANKING ENSEMBLES","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":2,"retrieve_with":"get_reference_implementation(name='DEEP RANKING ENSEMBLES')","origin_arxiv_id":"2303.15212"},{"name":"Self-training Ensembles","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":3,"retrieve_with":"get_reference_implementation(name='Self-training Ensembles')","origin_arxiv_id":"2106.15728"},{"name":"diverse ensembles with different data augmentation","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":3,"retrieve_with":"get_reference_implementation(name='diverse ensembles with different data augmentation')","origin_arxiv_id":"2007.04206"}],"code_nearby_caption":"Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.","origin_paper":{"arxiv_id":"1612.01474","page":"/paper/simple-and-scalable-predictive-uncertainty","syntology_url":"https://syntology.ai/paper/1612.01474","in_graph_layer":true,"samples":11,"ran":10,"n_ran_checked":9,"n_instrument":1,"unverified":1,"phrase":"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","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"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.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["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)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"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."}},"syntology_have_state":"loaded","record_sha256":"544682ca604e6a79a3d53ae261c747ab600c92e70a2274376d90cbc193d3e15a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}