Uncertainty Quantification

Uncertainty quantification (UQ) aims to assess and represent the confidence in predictions made by machine learning models, crucial for high-stakes applications where reliable predictions are paramount. Current research focuses on developing robust UQ methods, particularly addressing biases in predictions and efficiently quantifying uncertainty in large language models and deep neural networks, often employing techniques like conformal prediction, Bayesian methods, and ensemble learning. The ability to reliably quantify uncertainty enhances the trustworthiness and applicability of machine learning across diverse fields, from healthcare diagnostics and autonomous driving to climate modeling and drug discovery.

Papers

January 14, 2025

A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
Steven Landgraf, Rongjun Qin, Markus Ulrich
Foundation Model Uncertainty Quantification Monocular Depth Estimation Critical Synthesis Monocular Depth Metric Depth Metric Depth Estimation

January 12, 2025

Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach
Mathieu Cocheteux, Julien Moreau, Franck Davoine
Constructive Approach Uncertainty Quantification Conformal Prediction Sensor Fusion Extrinsic Calibration Sensor Calibration Uncertainty Awareness

January 10, 2025

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks
Ayush Khot, Xiwei Wang, Avik Roy, Volodymyr Kindratenko, Mark S. Neubauer
Uncertainty Quantification Distribution Detection Epistemic Uncertainty Deeper Network Evidential Deep Learning Jet Classification

January 8, 2025

January 6, 2025

Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements
Hanieh Mousavi, Jeff D. Eldredge
Uncertainty Quantification Aleatoric Uncertainty Aerodynamic Force Flow Reconstruction Gust Alleviation

January 5, 2025

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
Tianyang Wang, Yunze Wang, Jun Zhou, Benji Peng, Xinyuan Song, Charles Zhang, Xintian Sun, Qian Niu, Junyu Liu, Silin Chen, Keyu Chen, Ming Li, Pohsun Feng, Ziqian Bi, Ming Liu, Yichao Zhang, Cheng Fei, Caitlyn Heqi Yin, Lawrence KQ Yan
Artificial Intelligence Uncertainty Quantification High Uncertainty Anticipation Barzilai Borwein Technique Epistemic Uncertainty High Uncertainty Value Non Gaussian Aleatoric Uncertainty High Epistemic Uncertainty

January 2, 2025

Bayesian Active Learning By Distribution Disagreement
Thorben Werner, Lars Schmidt-Thieme
Active Learning Uncertainty Quantification Normalizing Flow Predictive Distribution Bayesian Active Learning Pool Based Active Learning

December 27, 2024

Uncertainty quantification for improving radiomic-based models in radiation pneumonitis prediction
Chanon Puttanawarut, Romen Samuel Wabina, Nat Sirirutbunkajorn
Uncertainty Quantification Radiomics Feature Radiation Oncology

December 24, 2024

Uncertainty Quantification in Stereo Matching
Wenxiao Cai, Dongting Hu, Ruoyan Yin, Jiankang Deng, Huan Fu, Wankou Yang, Mingming Gong
Uncertainty Quantification Stereo Matching High Uncertainty Value Prediction Confidence

December 23, 2024

Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion
Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, Sébastien Fournier
Uncertainty Quantification Multimodal Learning Multimodal AI Probabilistic Fusion Conflict Detection Belief Fusion

December 21, 2024

December 19, 2024

On Verbalized Confidence Scores for LLMs
Daniel Yang, Yao-Hung Hubert Tsai, Makoto Yamada
Large Language Model Uncertainty Quantification Confidence Score Calibrated Confidence

December 18, 2024

Uncertainty separation via ensemble quantile regression
Navid Ansari, Hans-Peter Seidel, Vahid Babaei
Uncertainty Quantification Epistemic Uncertainty Aleatoric Uncertainty Uncertainty Decomposition

December 17, 2024

Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework
Niloufar Eghbali, Tuka Alhanai, Mohammad M. Ghassemi
Uncertainty Quantification Accurate Treatment Conformal Predictor Mechanical Ventilation Conformalized Neural Network Ensemble

December 16, 2024

Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets
Yuxin Wang, Maresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Stefan Feuerriegel
Uncertainty Quantification Observational Data Confidence Interval Average Treatment Effect

December 14, 2024

Integrating Generative and Physics-Based Models for Ptychographic Imaging with Uncertainty Quantification
Canberk Ekmekci, Tekin Bicer, Zichao Wendy Di, Junjing Deng, Mujdat Cetin
Generative AI Uncertainty Quantification Imaging Technique Physic Based Model Iterative Reconstruction Bayesian Inversion X Ray Ptychography Coherent Diffraction Imaging

December 12, 2024

Conformal Prediction on Quantifying Uncertainty of Dynamic Systems
Aoming Liang, Qi Liu, Lei Xu, Fahad Sohrab, Weicheng Cui, Changhui Song, Moncef Gaubbouj
Uncertainty Quantification Dynamical System Conformal Prediction Ensemble Method High Uncertainty Value

December 11, 2024

Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling
Zaid Abulawi, Rui Hu, Prasanna Balaprakash, Yang Liu
Neural Network Uncertainty Quantification Bayesian Optimization Deep Ensemble Bayesian Perspective Aleatoric Uncertainty

Uncertainty Quantification

Papers

A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation

Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks

Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks

Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence

Bayesian Active Learning By Distribution Disagreement

Uncertainty quantification for improving radiomic-based models in radiation pneumonitis prediction

Uncertainty Quantification in Stereo Matching

Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

Condensed Stein Variational Gradient Descent for Uncertainty Quantification of Neural Networks

Uncertainty Quantification in Continual Open-World Learning

On Verbalized Confidence Scores for LLMs

Uncertainty separation via ensemble quantile regression

Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework

Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets

Integrating Generative and Physics-Based Models for Ptychographic Imaging with Uncertainty Quantification

Conformal Prediction on Quantifying Uncertainty of Dynamic Systems

Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling