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 31, 2023

Ensemble models outperform single model uncertainties and predictions for operator-learning of hypersonic flows
Victor J. Leon, Noah Ford, Honest Mrema, Jeffrey Gilbert, Alexander New
Human Prediction Uncertainty Quantification Uncertainty Estimation Operator Learning Ensemble Model Hypersonic Flow SciML Model

October 30, 2023

Uncertainty Quantification in Machine Learning Based Segmentation: A Post-Hoc Approach for Left Ventricle Volume Estimation in MRI
F. Terhag, P. Knechtges, A. Basermann, R. Tempone
Uncertainty Quantification Learning Based Biomedical Image Segmentation Post Hoc Robust Segmentation Left Ventricular Volume Estimation

October 25, 2023

October 19, 2023

October 18, 2023

Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
Julian Tachella, Marcelo Pereyra
Uncertainty Quantification Inverse Problem Parametric Bootstrap Scientific Image Intrinsic Uncertainty

October 17, 2023

October 13, 2023

Uncertainty Quantification using Generative Approach
Yunsheng Zhang
Deep Neural Network Generative Model Uncertainty Quantification Generative Approach MNIST Digit

October 12, 2023

Trustworthy Machine Learning
Bálint Mucsányi, Michael Kirchhof, Elisa Nguyen, Alexander Rubinstein, Seong Joon Oh
Uncertainty Quantification Distribution Generalization Trustworthy Machine Learning

October 10, 2023

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
Qianli Shen, Wai Hoh Tang, Zhun Deng, Apostolos Psaros, Kenji Kawaguchi
Uncertainty Quantification Physic Informed Physic Informed Learning Interacting System Probabilistic Guarantee

October 9, 2023

October 5, 2023

Uncertainty quantification for deep learning-based schemes for solving high-dimensional backward stochastic differential equations
Lorenc Kapllani, Long Teng, Matthias Rottmann
Uncertainty Quantification Backward Stochastic Differential Equation Numerical Scheme

October 4, 2023

ELUQuant: Event-Level Uncertainty Quantification in Deep Inelastic Scattering
Cristiano Fanelli, James Giroux
Uncertainty Quantification High Uncertainty Value Event Frame Bayesian Physic Informed Neural Network

October 3, 2023

Uncertainty Quantification in Inverse Models in Hydrology
Somya Sharma Chatterjee, Rahul Ghosh, Arvind Renganathan, Xiang Li, Snigdhansu Chatterjee, John Nieber, Christopher Duffy, Vipin Kumar
Uncertainty Quantification Inverse Problem Inverse Modeling Streamflow Prediction

September 28, 2023

Uncertainty Quantification for Eosinophil Segmentation
Kevin Lin, Donald Brown, Sana Syed, Adam Greene
Deep Learning Uncertainty Quantification Deep Bayesian Segmentation Eosinophil Instance Object Segmentation Eosinophilic Esophagitis

Uncertainty Quantification

Papers

Ensemble models outperform single model uncertainties and predictions for operator-learning of hypersonic flows

Uncertainty Quantification in Machine Learning Based Segmentation: A Post-Hoc Approach for Left Ventricle Volume Estimation in MRI

Distributed Uncertainty Quantification of Kernel Interpolation on Spheres

SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process

Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification

Approaches for Uncertainty Quantification of AI-predicted Material Properties: A Comparison

Uncertainty Quantification of Bandgaps in Acoustic Metamaterials with Stochastic Geometric Defects and Material Properties

Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems

Online Algorithms with Uncertainty-Quantified Predictions

On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction

Resampling Stochastic Gradient Descent Cheaply for Efficient Uncertainty Quantification

Uncertainty Quantification using Generative Approach

Trustworthy Machine Learning

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Making

A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods

Uncertainty quantification for deep learning-based schemes for solving high-dimensional backward stochastic differential equations

ELUQuant: Event-Level Uncertainty Quantification in Deep Inelastic Scattering

Uncertainty Quantification in Inverse Models in Hydrology

Uncertainty Quantification for Eosinophil Segmentation