Uncertainty Decomposition

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 32

All topics

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
Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification
Sep 30, 2026Gonzalo Esteban Mosquera Rojas, Sebastian R. van der Voort, Carolin M. Pirkl +3Uncertainty Quantification Brain Tumor Classification
Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, the Netherlands · Department of Medical Informatics, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands · GE HealthCare, Munich, Germany +3
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
Sep 28, 2026Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele +1Probabilistic Forecasting Shapley Value Attribution
Leibniz Institute for Prevention Research and Epidemiology – BIPS University of Bremen, Germany · Simula Research Laboratory Oslo, Norway · Telenor Research & Innovation Fornebu, Norway +1
Not All Confusion Is Equal: A Source-Aware Uncertainty Diagnosis for Fine-Grained Aircraft Detection
Sep 24, 2026Hai Huang, Helmut MayerObject Detection Fine-Grained Visual Perception
Chair of Visual Computing, Institute for Applied Computer Science, Universität der Bundeswehr München, Germany
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
Estimating Uncertainty in Galaxy Morphology Classification
Aug 9, 2026Kai Cheng, Ruoqi Wang, Qiong LuoUncertainty Quantification Uncertainty Decomposition
The Hong Kong University of Science and Technology, Hong Kong, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
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
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
Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
Aug 5, 2026Zhen Zhang, Amr AlanwarUncertainty Quantification Probabilistic Forecasting
School of Computation, Information and Technology, Technical University of Munich, Germany
Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Models
Aug 1, 2026Yibin DongUncertainty Quantification World Models
Shandong University
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
CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
Jun 30, 2026Sanghyuk Chun, William Yang, Amaya Dharmasiri +1Uncertainty Quantification Multimodal Large Language Models
Princeton University
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
Uncertainty Decomposition for Clarification Seeking in LLM Agents
Jun 17, 2026Gregory MatsnevLLM Agents LLM Uncertainty Estimation
AI Talent Hub, ITMO University Saint Petersburg 197101, Russia
Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty
Jun 15, 2026Baishali Chaudhury, Mengdie Flora Wang, Hyunji Hayley Park +3Reasoning Consistency in Language Models LLM Reliability
AWS Generative AI Innovation Center
Epistemic Uncertainty Is Not the Reducible Kind
Jun 10, 2026Robin YoungUncertainty Quantification Uncertainty Decomposition
University of Cambridge
Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP
May 23, 2026Keito Inoshita, Takato UenoSoft-Label Learning Bayesian Neural Networks
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
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
Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations
May 21, 2026Birgit Kühbacher, Daan Crommelin, Niki KilbertusUncertainty Quantification Chaotic Dynamical Systems
Technical University of Munich, Munich, Germany · Helmholtz Munich, Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany +2
Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems
May 14, 2026Yuxin Guo, Dongrui Deng, Pulkit GroverUncertainty Quantification Bayesian Inverse Problems
1Neuroscience Institute, Carnegie Mellon University · 2Machine Learning Department, Carnegie Mellon University · Department of Electrical and Computer Engineering, Carnegie Mellon University
Flexible Routing via Uncertainty Decomposition
May 8, 2026Charlotte Peale, Siddartha Devic, Parikshit Gopalan +2Uncertainty Quantification Adaptive Model Routing
1Stanford University · University of Southern California · 3Apple
ConformaDecompose: Explaining Uncertainty via Calibration Localization
Apr 29, 2026Fatima Rabia Yapicioglu, Meltem Aksoy, Alberto Rigenti +4Uncertainty Quantification Conformal Prediction
Department of Computer Science and Engineering, University of Bologna, Italy · Marketing and Sales, Automobili Lamborghini S.p.A, Sant’Agata Bolognese, Italy · RCT Data Science and Security, Technical University Dortmund, Germany +4
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
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
Apr 18, 2026Kimia Hamidieh, Veronika Thost, Walter Gerych +2Selective Prediction Confidence Estimation in Language Models
1MIT · MIT-IBM Watson AI Lab · 3WPI +1
An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
Mar 31, 2026Nils Grünefeld, Jes Frellsen, Christian HardmeierUncertainty Quantification LLM Uncertainty Estimation
1IT University of Copenhagen · 3Pioneer Centre for Artificial Intelligence · 2Technical University of Denmark
Quantification of Credal Uncertainty: A Distance-Based Approach
Mar 28, 2026Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann +6Uncertainty Quantification Aleatoric Uncertainty
Dept. of Statistics, CS & Mathematics, Public Univ. of Navarre · EPIC Lab, Nanyang Technological Univ. Singapore · Rational Intelligence Lab, CISPA Helmholtz Center for Information Security +7
The Anatomy of Uncertainty in LLMs
Mar 26, 2026Aditya Taparia, Ransalu Senanayake, Kowshik Thopalli +1LLM Auditing LLM Reliability
School of Computing and Augmented Intelligence, Arizona State University · Lawrence Livermore National Laboratory
Rethinking Uncertainty Quantification and Entanglement in Image Segmentation
Mar 19, 2026Jakob Lønborg Christensen, Vedrana Andersen Dahl, Morten Rieger Hannemose +2Uncertainty Quantification Deep Ensembles
Technical University of Denmark, DTU Compute · University of Lucerne, Faculty of Health Sciences and Medicine, Switzerland
Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
Feb 24, 2026Mame Diarra Toure, David A. StephensBayesian Neural Networks Classification
Department of Mathematics and Statistics , McGill University

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

Structural Limits of the Information-Theoretic Uncertainty Decomposition

Jakob Lønborg Christensen, Christian F. Baumgartner, Morten Rieger Hannemose, Anders Bjorholm Dahl+1

DTU Compute Technical University of Denmark · Faculty of Health Sciences and Medicine University of Lucerne

Aleatoric Uncertainty Information-Theoretic Lower Bounds Uncertainty Decomposition Epistemic Uncertainty

Open paper AskPDF arXiv

Uncertainty estimation in machine learning typically decomposes uncertainty into aleatoric uncertainty (AU) and epistemic uncertainty (EU) using the standard information-theoretic framework. However, in practice, two critical issues arise: entanglement (AU and EU are highly correlated) and epistemic collapse (EU magnitude shrinks with increasing model capacity). We analyze this framework on a functional level and discover that significant portions of the assumed AU, EU range are infeasible in finite settings, and cannot be attained with any class probabilities. We characterize how this infeasible region scales with the number of classes and Monte Carlo samples

N

(e.g., from ensembles with

N

members), revealing it is bounded by

\text{AU} \leq \log(2)/N

. Crucially, the infeasible region's boundary helps explain epistemic collapse: when model confidence is high,

\text{AU} > \text{EU}

is guaranteed by this fundamental structural limitation. Our findings show that increasing ensemble size mitigates epistemic collapse by reducing the infeasible area. Lastly, we caution against interpreting AU and EU as independent quantities in low AU regimes, since we show they are coupled when

\text{AU} \leq \log(2)/N

Momentum

Related topics

Latest papers 32