Aleatoric Uncertainty

Follow this topic Ask about this topic

Aleatoric uncertainty describes variability that remains even when a model has learned the available patterns, such as measurement noise, ambiguous labels, or inherently stochastic outcomes. Researchers estimate it with predictive distributions, heteroscedastic models, and probabilistic or Bayesian methods, often separating it from epistemic uncertainty caused by limited knowledge. Evaluation commonly examines calibration, predictive intervals, proper scoring rules, and whether uncertainty tracks independent signals such as annotator disagreement or changing noise levels. A central challenge is that estimates depend on how uncertainty is defined and modeled, and separating irreducible variability from model error is not always identifiable or reliable.

Latest papers

44 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance
Oct 21, 2026Navodita Sharma, Abhishek Shetty, Max Simchowitz +1Conditional Flow Matching Conditional Distribution Estimation
Massachusetts Institute of Technology · Georgia Institute of Technology · Carnegie Mellon University
Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction
Oct 13, 2026Anton Arapin, Aditya Singh, Yixin Wang +2Aleatoric Uncertainty Action-Conditioned World Models
University of Michigan · NVIDIA
Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity
Oct 6, 2026Mani Kumar Tellamekala, Tosh Brown, Michel ValstarAleatoric Uncertainty Bayesian Inference
Amsterdam, The Netherlands · BlueSkeye AI · University of Nottingham, U.K.
Structural Limits of the Information-Theoretic Uncertainty Decomposition
Sep 30, 2026Jakob Lønborg Christensen, Christian F. Baumgartner, Morten Rieger Hannemose +2Aleatoric Uncertainty Information-Theoretic Lower Bounds
DTU Compute Technical University of Denmark · Faculty of Health Sciences and Medicine University of Lucerne
Radiomap Blind Prediction under Incomplete Observation: Error Characterization and Correctable Propagation-Prior Learning
Sep 26, 2026Xiaojie Li, Yu Han, Han Fang +4Radio Propagation Modeling Learning with Missing Data
School of Information Science and Engineering, Southeast University, Nanjing 210096, China · National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China · School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China +3
Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors
Sep 24, 2026Taiabur Rahman, Siddiqur Rahman, Muhammad Moniruzzaman +7Clinical Outcome Prediction Aleatoric Uncertainty
AI-MIQA, www.ai-miqa.eu. · Vision Eye Institute and Hospital, Dhaka, 1205, Bangladesh. · China West Normal University, Nanchong, Sichuan, China.
Decomposing LLM-Judge Uncertainty to Target Expert Labels
Sep 6, 2026Ryan LailAnnotator Disagreement LLM-as-a-Judge
Composo AI
From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs
Sep 3, 2026Omer Nahum, Niv Nayman, Jonathan Fhima +4LLM Uncertainty Estimation Aleatoric Uncertainty
Data and Decision Sciences, Technion, Israel · Amazon Web Services · Computer Vision Group, University of Bern, Switzerland
Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
Aug 31, 2026Rodrigo Almeida, Noelia Otero, Jost Arndt +3Probabilistic Forecasting Aleatoric Uncertainty
Applied Machine Learning Group, Fraunhofer Heinrich-Hertz Institute, 10587 Berlin, Germany · Department of Electrical Engineering and Computer Science, Technische Universität Berlin, 10587 Berlin, Germany · BIFOLD - Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
FiLM-GPNet: Geometry-Aware Pseudo-Supervised Phase Restoration with Zero-Shot Generalization for Large Temporal InSAR Stacks
Aug 29, 2026Getnet Demil, Muhammad Farhan Humayun, Tomi Westerlund +2Aleatoric Uncertainty Synthetic Aperture Radar
University of Turku Turku, Finland
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
Aug 7, 2026Pierre Nodet, Thomas GeorgeUncertainty Quantification Aleatoric Uncertainty
Orange Research, Châtillon, France
UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression
Aug 6, 2026Jacek KomorowskiScene Coordinate Regression Uncertainty Quantification
Warsaw University of Technology, Warsaw, Poland
A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk
Aug 6, 2026Frieder Wizgall, Georg Tirpitz, Moritz Seiler +2Uncertainty Quantification Aleatoric Uncertainty
University of Tübingen, Tübingen, Germany · Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Bernstein Center for Computational Neuroscience Berlin, Berlin, Germany +2
Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
Jul 27, 2026Mariela De Lucas Álvarez, Melvin Laux, Arthur de Freitas Precht +4Spacecraft Attitude Determination Residual Learning
Robotics Innovation Center, German Research Center for AI (DFKI GmbH), Bremen, Germany · Airbus Defence and Space GmbH, Immenstaad, Germany
Disentangling Model and Human Data Uncertainty in Apparent Facial Age Estimation
Jul 17, 2026Andrei Foitos, Ivo Pascal de Jong, Matias Valdenegro-ToroBayesian Neural Networks Uncertainty Quantification
Bernoulli Institute, University of Groningen, Groningen, NL
Subjective Risk Decomposition: A New View for Uncertainty Quantification
Jul 16, 2026Raghad Alamri, Michele Caprio, Gavin BrownUncertainty Quantification Aleatoric Uncertainty
Department of Computer Science, The University of Manchester · Department of Computer Science, University of Warwick
Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
Jul 3, 2026Lin Li, Li Rong Wang, Hsuan Fu +1Reinforcement Learning Uncertainty Quantification
Nanyang Technological University 50 Nanyang Avenue, Singapore · Nanyang Technological University Centre for Frontier AI Research, A*STAR 50 Nanyang Avenue, Singapore · Laval University Quebec, Canada
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition
Jun 21, 2026Keito Inoshita, Takato UenoUncertainty Quantification Selective Prediction
Faculty of Business and Commerce, Kansai University, Suita, Japan · Data Science and AI Innovation Research Promotion Center, Shiga University, Hikone, Japan · Graduate School of Data Science, Shiga University, Hikone, Japan
On the QUEST for Uncertainty Quantification via Highest Density Regions
Jun 17, 2026Sam Goring, Tom Kuipers, Nicola Paoletti +1Uncertainty Quantification Aleatoric Uncertainty
King’s College London · Northeastern University London
Hybrid Uncertainty Sensitivity Analysis Based on the HSIC for High-Dimensional Responses with Aleatory--Epistemic Separation
Jun 12, 2026Shijie Zhong, Jiangfeng Fu, Pengfei WeiUncertainty Quantification Aleatoric Uncertainty
School of Power and Energy Northwestern Polytechnical University Xi’an, Shanxi 710129
What Uncertainties Do We Need for Dynamical Systems?
Jun 10, 2026Yusuf Sale, Christopher Bülte, Felix Czaja +2Dynamical Systems Uncertainty Quantification
Institute of Computer Science, LMU Munich · Munich · Department of Mathematics, LMU Munich +1
Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classification
Jun 8, 2026Cornelius Schröder, Žygimantas Marcinkus, Markus LienkampLidar-Based 3D Object Detection Uncertainty Quantification
Institute for Automotive Engineering, Munich Institute of Robotics and Machine Intelligence, School of Engineering and Design, Technical University of Munich
Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning
May 25, 2026Waleed Razzaq, Yun-Bo ZhaoRepresentation Learning Uncertainty Quantification
Department of Automation, University of Science & Technology of China, Hefei, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
May 21, 2026Yinsong Chen, Samson S. Yu, Kashem M. MuttaqiUncertainty Quantification Time Series Forecasting
School of Engineering, Deakin University, Melbourne, VIC 3216, Australia · ARC Training Centre in Energy Technologies for Future Grids, School of Engineering, University of Wollongong, Wollongong, NSW 2522, Australia
GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
May 13, 2026Mayank Nautiyal, Li Ju, Andreas Hellander +2Cross-Modal Learning Flow Matching
Department of Information Technology, Uppsala University, Uppsala, Sweden · SciLifeLab, Uppsala University, Uppsala, Sweden
The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
May 8, 2026Santiago Cortes-Gomez, Mateo Dulce Rubio, Carlos Patino +1Aleatoric Uncertainty Decision-Making under Uncertainty
Machine Learning Department, Carnegie Mellon University · Center for Data Science, New York University · University of Amsterdam
Confidence Estimation in Automatic Short Answer Grading with LLMs
Apr 30, 2026Longwei Cong, Sonja Hahn, Sebastian Gombert +3Uncertainty Quantification Selective Prediction
DIPF | Leibniz Institute for Research and Information in Education, 60323 Frankfurt am Main, Germany · Faculty of Computer Science, Goethe University Frankfurt, 60629 Frankfurt am Main, Germany · Chemnitz University of Technology, 09111 Chemnitz, Germany
Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
Apr 29, 2026Disha SinghaReward Hacking Reinforcement Learning
Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence
Apr 28, 2026Jinseok Chung, Minkyoung Song, Hyunji Jung +1Uncertainty Quantification In-Context Learning
POSTECH
Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition
Apr 27, 2026Tanmoy Mukherjee, Thomas Bailleux, Pierre Marquis +1Uncertainty Quantification Concept Bottleneck Models
Univ. Artois, CNRS, CRIL, France · Institut Universitaire de France

Oct 21, 2026J/K move · Enter open · S save

Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance

Navodita Sharma, Abhishek Shetty, Max Simchowitz, Pulkit Agrawal

Massachusetts Institute of Technology · Georgia Institute of Technology · Carnegie Mellon University

Conditional Flow Matching Conditional Distribution Estimation Epistemic Uncertainty Aleatoric Uncertainty

Open paper AskPDF arXiv

Conditional Flow Models (CFMs) are increasingly being used in place of deterministic predictors across machine learning, including for tasks that were classically formulated as regression. Given their success in such tasks, we ask the question: what useful information do the conditional distributions produced by CFMs carry beyond what a point predictor would provide? We identify a systematic phenomenon: in many natural regimes, CFM samples routinely have larger variance than the true conditional distribution, even in nearly deterministic regression problems. This effect is most pronounced where the model has not resolved the dependence on the conditioning variable, and thus the additional variance can be viewed as converting epistemic uncertainty in fitting the ground truth conditional distribution into apparent aleatoric variance in the generated samples. Through controlled synthetic and real-data experiments, and comparisons with explicit smoothing estimators, we show that the induced variance tracks model underfitting of complex or hard-to-fit targets, and decreases with additional training or data. We provide a theoretical account of the phenomenon in a simplified setting and demonstrate a consequent practical use-case of conditional flow-matching: designing high-coverage predictive sets that cover the ground-truth regression target.