mlsanityData to 14 Oct 2026

CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk

arXiv 2507.08150 ↗First posted 10 Jul 2025stat.ML cs.LG stat.MEcited by 6

Not on the map. Why?

Abstract (arXiv)

Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in a balanced manner. We propose CLEAR, a calibration method with two distinct parameters, γ1 and γ2, to combine the two uncertainty components and improve the conditional coverage of predictive intervals for regression tasks. CLEAR is compatible with any pair of aleatoric and epistemic estimators; we show how it can be used with (i) quantile regression for aleatoric uncertainty and (ii) ensembles drawn from the Predictability-Computability-Stability (PCS) framework for epistemic uncertainty. Across 17 diverse real-world datasets, CLEAR achieves an average improvement of 28.3% and 17.5% in the interval width compared to the two individually calibrated baselines while maintaining nominal coverage. Similar improvements are observed when applying CLEAR to Deep Ensembles (epistemic) and Simultaneous Quantile Regression (aleatoric). The benefits are especially evident in scenarios dominated by high aleatoric or epistemic uncertainty. Project page: https://unco3892.github.io/clear/

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 46 of its 95 references that are in the map. First posted on arXiv 10 Jul 2025.

Builds on

46 of 95 references.

References · 46

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  8. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  9. 2019Conformalized Quantile Regressioncited by 629
  10. 2015Weight Uncertainty in Neural Networkscited by 554
  11. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
  12. 2020Classification with Valid and Adaptive Coveragecited by 396
34 more
  1. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  2. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  3. 2021Transformers Can Do Bayesian Inferencecited by 360
  4. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  5. 2020Training independent subnetworks for robust predictioncited by 177
  6. 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 150
  7. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  8. 2021Localized Conformal Prediction: A Generalized Inference Framework for Conformal Predictioncited by 114
  9. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  10. 2014Consistency of random forestscited by 85
  11. 2019Veridical Data Sciencecited by 66
  12. 2024Variational Learning is Effective for Large Deep Networkscited by 65
  13. 2019Greed is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisationcited by 51
  14. 2019Function Space Particle Optimization for Bayesian Neural Networkscited by 41
  15. 2020Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filteringcited by 34
  16. 2017Fast calibrated additive quantile regressioncited by 27
  17. 2024Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rulescited by 21
  18. 2020Stable discovery of interpretable subgroups via calibration in causal studiescited by 18
  19. 2021Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imagingcited by 18
  20. 2023Integrating Uncertainty Awareness into Conformalized Quantile Regressioncited by 17
  21. 2021NOMU: Neural Optimization-based Model Uncertaintycited by 16
  22. 2022UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANscited by 16
  23. 2025PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Frameworkcited by 9
  24. 2022Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEscited by 7
  25. 2023Retrospective Uncertainties for Deep Models using Vine Copulascited by 7
  26. 2019Online Learning with Continuous Ranked Probability Scorecited by 6
  27. 2023Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Frameworkcited by 6
  28. 2024Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibrationcited by 6
  29. 2023Structural restrictions in local causal discovery: identifying direct causes of a target variablecited by 5
  30. 2024Variational Low-Rank Adaptation Using IVONcited by 5
  31. 2021How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterizationcited by 4
  32. 2024Learning Chaotic Systems and Long-Term Predictions with Neural Jump ODEscited by 3
  33. 2021Analytically Tractable Hidden-States Inference in Bayesian Neural Networkscited by 2
  34. 2024SEMF: Supervised Expectation-Maximization Framework for Predicting Intervalscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2026Uncertainty-Aware Reward Modeling for Stable RLHFcited by 6
  2. 2026Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judgescited by 5
  3. 2025Cross-World Assumption and Refining Prediction Intervals for Individual Treatment Effectscited by 1
  4. 2026Retrospective Counterfactual Prediction by Conditioning on the Factual Outcome: A Cross-World Approachcited by 1
  5. 2026Conformal Calibration for Multi-Modal Regression with Missing Modalitiescited by 1
  6. 2026Missingness-Aware Conformal Prediction Under Cross-Hospital Distribution Shiftcited by 0