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

October 12, 2022

October 10, 2022

Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency
Language Model Natural Language Processing Fine Tuning Pre Trained Language Model Uncertainty Quantification PLM Based Large Scale Analysis

October 6, 2022

Bayesian Nonlocal Operator Regression (BNOR): A Data-Driven Learning Framework of Nonlocal Models with Uncertainty Quantification
Yiming Fan, Marta D'Elia, Yue Yu, Habib N. Najm, Stewart Silling
Uncertainty Quantification Data Driven Learning Heterogeneous Material Nonlocal Model Operator Regression

October 5, 2022

Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis
Benjamin Lambert, Florence Forbes, Alan Tucholka, Senan Doyle, Harmonie Dehaene, Michel Dojat
Deep Learning Deep Learning Model Uncertainty Quantification Uncertainty Estimation Medical Image Analysis Clinical Artificial Intelligence

September 30, 2022

September 28, 2022

Label Noise Robustness of Conformal Prediction
Bat-Sheva Einbinder, Shai Feldman, Stephen Bates, Anastasios N. Angelopoulos, Asaf Gendler, Yaniv Romano
Native Robustness Uncertainty Quantification Ground Truth Conformal Prediction Label Noise

September 20, 2022

Calibrating Ensembles for Scalable Uncertainty Quantification in Deep Learning-based Medical Segmentation
Thomas Buddenkotte, Lorena Escudero Sanchez, Mireia Crispin-Ortuzar, Ramona Woitek, Cathal McCague, James D. Brenton, Ozan Öktem, Evis Sala, Leonardo Rundo
Active Learning Uncertainty Quantification Image Processing Uncertainty Measure Deep Learning Based Medical

September 19, 2022

Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
Niko Sünderhauf, Jad Abou-Chakra, Dimity Miller
Neural Radiance Field Uncertainty Quantification Epistemic Uncertainty Model Uncertainty Predictive Uncertainty NeRF Method

September 17, 2022

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network
Takuya Kanazawa, Chetan Gupta
Uncertainty Quantification Single Neural Network Predictive Distribution Deterministic Neural Network Uncertainty Sampling Uncertainty Quantification Method Point Forecasting

September 16, 2022

Uncertainty Quantification of Collaborative Detection for Self-Driving
Sanbao Su, Yiming Li, Sihong He, Songyang Han, Chen Feng, Caiwen Ding, Fei Miao
Autonomous Driving Autonomous Vehicle Uncertainty Quantification Collaborative Object

September 9, 2022

Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty Quantification
Renat Sergazinov, Mohammadreza Armandpour, Irina Gaynanova
Deep Learning Model Uncertainty Quantification Glucose Prediction Glucose Data

September 8, 2022

Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey
Sophia Sun
Deep Learning Timely Survey Uncertainty Quantification High Uncertainty Anticipation Conformal Prediction SpatioTemporal Data Conformal Method

September 7, 2022

Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?
Lisa Wimmer, Yusuf Sale, Paul Hofman, Bern Bischl, Eyke Hüllermeier
Machine Learning Uncertainty Quantification Mutual Information Epistemic Uncertainty Information Theory Conditional Entropy Non Gaussian Aleatoric Uncertainty

September 5, 2022

Ensemble of Pre-Trained Neural Networks for Segmentation and Quality Detection of Transmission Electron Microscopy Images
Arun Baskaran, Yulin Lin, Jianguo Wen, Maria K. Y. Chan
Uncertainty Quantification Segmentation Based Approach Diverse Ensemble Microscopy Image ImageNet Dataset Bayesian Model Electron Microscopy Pre Trained Neural Network Quality Related Anomaly Detection

August 27, 2022

A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives
Adam Thelen, Xiaoge Zhang, Olga Fink, Yan Lu, Sayan Ghosh, Byeng D. Youn, Michael D. Todd, Sankaran Mahadevan, Chao Hu, Zhen Hu
Optimization Purpose Uncertainty Quantification Digital Twin Synthesized View 3D Model

August 25, 2022

NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operators
Zongren Zou, Xuhui Meng, Apostolos F Psaros, George Em Karniadakis
Physic Informed Neural Network Uncertainty Quantification Differential Equation Scientific Machine Learning Feature Operator Computational Analysis SciML Model

August 24, 2022

Calibrated and Enhanced NRLMSIS 2.0 Model with Uncertainty Quantification
Richard J. Licata, Piyush M. Mehta, Daniel R. Weimer, W. Kent Tobiska, Jean Yoshii
Full Model Uncertainty Quantification Atmospheric Model Global Calibration Thermospheric Density

August 11, 2022

Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks
Dingyi Zhuang, Shenhao Wang, Haris N. Koutsopoulos, Jinhua Zhao
Uncertainty Quantification Spatio Temporal Gene Level GNN Temporal Graph Neural Network Travel Demand

Uncertainty Quantification

Papers

Quantifying Uncertainty with Probabilistic Machine Learning Modeling in Wireless Sensing

JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks

Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis

Bayesian Nonlocal Operator Regression (BNOR): A Data-Driven Learning Framework of Nonlocal Models with Uncertainty Quantification

Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis

Leveraging Industry 4.0 -- Deep Learning, Surrogate Model and Transfer Learning with Uncertainty Quantification Incorporated into Digital Twin for Nuclear System

Physically Meaningful Uncertainty Quantification in Probabilistic Wind Turbine Power Curve Models as a Damage Sensitive Feature

Label Noise Robustness of Conformal Prediction

Calibrating Ensembles for Scalable Uncertainty Quantification in Deep Learning-based Medical Segmentation

Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

Uncertainty Quantification of Collaborative Detection for Self-Driving

Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty Quantification

Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey

Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?

Ensemble of Pre-Trained Neural Networks for Segmentation and Quality Detection of Transmission Electron Microscopy Images

A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives

NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operators

Calibrated and Enhanced NRLMSIS 2.0 Model with Uncertainty Quantification

Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks