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.

487papers

Papers - Page 25

February 8, 2023

Fortuna: A Library for Uncertainty Quantification in Deep Learning
Uncertainty Quantification Deep Learning Deep Neural Network Reliable Uncertainty Easy to Use Library

February 7, 2023

IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning
Deep Regression Information Bottleneck Neural Operator Poor Extrapolation Performance Uncertainty Quantification Method Uncertainty Quantification Confidence Map

February 2, 2023

January 18, 2023

Physics-informed Information Field Theory for Modeling Physical Systems with Uncertainty Quantification
Uncertainty Quantification Information Field Theory Langevin Dynamic Model Uncertainty Physical System

January 13, 2023

December 28, 2022

A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems
Uncertainty Quantification Uncertainty Information Probability Measure Application Proficiency Parameter Uncertainty

December 24, 2022

Improving Uncertainty Quantification of Variance Networks by Tree-Structured Learning
Variance Network Neural Network Uncertainty Quantification Tree Learning

December 20, 2022

Uncertainty Quantification of MLE for Entity Ranking with Covariates
Uncertainty Quantification Maximum Likelihood Relevant Covariates Latent Feature Ranking Performance

December 15, 2022

Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls
Uncertainty Quantification Molecular Dynamic Coarse Grained Neural Network Potential Promise Common Pitfall

December 13, 2022

Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
Uncertainty Quantification Quality Regression Network Regression Network Prediction Interval Target Prediction

December 8, 2022

Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks
Prediction Accuracy Convolutional Neural Network Carbon Sequestration Carbon Capture Seismic Inversion Uncertainty Quantification Real Data

November 29, 2022

UQ-ARMED: Uncertainty quantification of adversarially-regularized mixed effects deep learning for clustered non-iid data
Explainable Metric Ensemble Method Uncertainty Quantification Non IID Data Ensemble Model

Uncertainty Quantification

Papers - Page 25

Fortuna: A Library for Uncertainty Quantification in Deep Learning

IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning

Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications

Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

Physics Constrained Motion Prediction with Uncertainty Quantification

Randomized prior wavelet neural operator for uncertainty quantification

Physics-informed Information Field Theory for Modeling Physical Systems with Uncertainty Quantification

A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows

Uncertainty Quantification for Local Model Explanations Without Model Access

A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems

Improving Uncertainty Quantification of Variance Networks by Tree-Structured Learning

Uncertainty Quantification of MLE for Entity Ranking with Covariates

Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Uncertainty Quantification for Deep Neural Networks: An Empirical Comparison and Usage Guidelines

Error-Aware B-PINNs: Improving Uncertainty Quantification in Bayesian Physics-Informed Neural Networks

Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation

Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks

UQ-ARMED: Uncertainty quantification of adversarially-regularized mixed effects deep learning for clustered non-iid data