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

November 26, 2022

Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification
Xing Yan, Yonghua Su, Wenxuan Ma
Uncertainty Quantification Adaptive Importance Quantile Regression Conditional Distribution Conditional Probability Distribution Prediction

November 16, 2022

Prediction and Uncertainty Quantification of SAFARI-1 Axial Neutron Flux Profiles with Neural Networks
Lesego E. Moloko, Pavel M. Bokov, Xu Wu, Kostadin N. Ivanov
Neural Network Human Prediction Uncertainty Quantification Nuclear Reactor Experimental Verification Nuclear Engineering

November 10, 2022

Robust DNN Surrogate Models with Uncertainty Quantification via Adversarial Training
Lixiang Zhang, Jia Li
Adversarial Training Uncertainty Quantification Surrogate Model

November 8, 2022

Gradient-enhanced deep neural network approximations
Xiaodong Feng, Li Zeng
Deep Neural Network Uncertainty Quantification Gradient Based Efficient Uncertainty Estimation Deep Neural Network Approximation

November 7, 2022

Uncertainty Quantification for Atlas-Level Cell Type Transfer
Jan Engelmann, Leon Hetzel, Giovanni Palla, Lisa Sikkema, Malte Luecken, Fabian Theis
Uncertainty Quantification Single Cell Cell Classification Cell Type Cell Clustering Cell Identity

November 4, 2022

Materials Property Prediction with Uncertainty Quantification: A Benchmark Study
Daniel Varivoda, Rongzhi Dong, Sadman Sadeed Omee, Jianjun Hu
Uncertainty Quantification Uncertainty Estimation Benchmark Study Material Property Prediction

November 3, 2022

October 31, 2022

October 30, 2022

A view on model misspecification in uncertainty quantification
Yuko Kato, David M. J. Tax, Marco Loog
Machine Learning Model Human Prediction Uncertainty Quantification High Uncertainty Anticipation Uncertainty Estimation Best View Model Misspecification

October 26, 2022

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification
Botond Fazekas, Dmitrii Lachinov, Guilherme Aresta, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
Uncertainty Quantification Segmentation Based Approach Optical Coherence Tomography Anatomical Prior Soft Membrane Membrane Segmentation

October 23, 2022

On double-descent in uncertainty quantification in overparametrized models
Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
Full Model Uncertainty Quantification Overparametrization Bound Double Descent Uncertainty Measure Overconfident Prediction

October 21, 2022

Bayesian deep learning framework for uncertainty quantification in high dimensions
Jeahan Jung, Minseok Choi
Uncertainty Quantification Bayesian Neural Network Bayesian Inference High Dimension Bayesian Deep Learning Hamiltonian Monte Carlo

October 18, 2022

Uncertainty in Extreme Multi-label Classification
Jyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhong, Cho-Jui Hsieh, Hsiang-Fu Yu
Uncertainty Quantification High Uncertainty Anticipation Supervised Baseline Extreme Multi Label Instance Wise Uncertainty

October 16, 2022

Posterior Regularized Bayesian Neural Network Incorporating Soft and Hard Knowledge Constraints
Jiayu Huang, Yutian Pang, Yongming Liu, Hao Yan
Uncertainty Quantification Bayesian Neural Network Posterior Mode Neural Network Parameter Bayesian Regularization

October 14, 2022

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney
Gaussian Process Uncertainty Quantification Uncertainty Estimation Data Dimensionality Cross Validation Double Descent Partial Monotonicity Marginal Likelihood Empirical Bayes

Uncertainty Quantification

Papers

Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification

Prediction and Uncertainty Quantification of SAFARI-1 Axial Neutron Flux Profiles with Neural Networks

The Implicit Delta Method

Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models

Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression

Robust DNN Surrogate Models with Uncertainty Quantification via Adversarial Training

Gradient-enhanced deep neural network approximations

Uncertainty Quantification for Atlas-Level Cell Type Transfer

Materials Property Prediction with Uncertainty Quantification: A Benchmark Study

Uncertainty Quantification for Rule-Based Models

Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification

Homodyned K-distribution: parameter estimation and uncertainty quantification using Bayesian neural networks

Evaluating Point-Prediction Uncertainties in Neural Networks for Drug Discovery

A view on model misspecification in uncertainty quantification

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification

On double-descent in uncertainty quantification in overparametrized models

Bayesian deep learning framework for uncertainty quantification in high dimensions

Uncertainty in Extreme Multi-label Classification

Posterior Regularized Bayesian Neural Network Incorporating Soft and Hard Knowledge Constraints

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes