Model Uncertainty

Model uncertainty, encompassing both aleatoric (irreducible) and epistemic (reducible) sources of error, is a critical area of research aiming to improve the reliability and trustworthiness of machine learning models. Current efforts focus on quantifying and decomposing these uncertainties across various model architectures, including deep neural networks, boosted trees, and Bayesian methods, often employing techniques like Monte Carlo dropout, ensembles, and conformal prediction. Understanding and effectively managing model uncertainty is crucial for building robust and safe AI systems, particularly in high-stakes applications like healthcare, finance, and climate modeling, where reliable predictions are paramount. This improved understanding facilitates better decision-making under uncertainty and enhances the overall trustworthiness of AI-driven insights.

Papers

May 2, 2024

April 29, 2024

Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks
Javier Antoran
Neural Network Deep Learning Deep Neural Network Deep Learning Model Gaussian Process New Era Model Uncertainty Posterior Sampling Neural Network Inference Scalable Bayesian

March 26, 2024

R2D2 image reconstruction with model uncertainty quantification in radio astronomy
Amir Aghabiglou, Chung San Chu, Arwa Dabbech, Yves Wiaux
High Dynamic Range Model Uncertainty Residual Network Residual Image Radio Astronomy Image Estimation

March 25, 2024

Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process
Kevin S. Miller, Adam J. Thorpe, Ufuk Topcu
Active Learning Model Uncertainty Sampling Technique Active Learning Algorithm Prior Model

March 21, 2024

Model Uncertainty in Evolutionary Optimization and Bayesian Optimization: A Comparative Analysis
Hao Hao, Xiaoqun Zhang, Aimin Zhou
Comparative Study Bayesian Optimization Surrogate Model Model Uncertainty Evolutionary Optimization Model Based Optimization Surrogate Assisted Evolutionary Algorithm

March 14, 2024

Uncertainty Quantification for cross-subject Motor Imagery classification
Prithviraj Manivannan, Ivo Pascal de Jong, Matias Valdenegro-Toro, Andreea Ioana Sburlea
Uncertainty Quantification Epistemic Uncertainty Model Uncertainty Motor Imagery Classification

March 9, 2024

Providing Safety Assurances for Systems with Unknown Dynamics
Hao Wang, Javier Borquez, Somil Bansal
System Description Autonomous System Model Uncertainty Unknown Dynamic Learned Dynamic Safety Assurance Ensemble Uncertainty

February 22, 2024

Uncertainty-Aware Evaluation for Vision-Language Models
Vasily Kostumov, Bulat Nutfullin, Oleg Pilipenko, Eugene Ilyushin
Vision Language Model Vision Language Visual Question Answering Model Uncertainty

February 17, 2024

OneBit: Towards Extremely Low-bit Large Language Models
Yuzhuang Xu, Xu Han, Zonghan Yang, Shuo Wang, Qingfu Zhu, Zhiyuan Liu, Weidong Liu, Wanxiang Che
Language Model Model Compression Model Uncertainty P Bit Image Quantization

February 9, 2024

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
Maohao Shen, J. Jon Ryu, Soumya Ghosh, Yuheng Bu, Prasanna Sattigeri, Subhro Das, Gregory W. Wornell
Epistemic Uncertainty Model Uncertainty Evidential Deep Learning Predictive Uncertainty Quantification

January 16, 2024

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Kim-Celine Kahl, Carsten T. Lüth, Maximilian Zenk, Klaus Maier-Hein, Paul F. Jaeger
Semantic Segmentation New Framework Uncertainty Estimation Model Uncertainty Policy Value Uncertainty Estimation Method Quantitative Validation

January 7, 2024

Uncertainty Quantification on Clinical Trial Outcome Prediction
Tianyi Chen, Yingzhou Lu, Nan Hao, Capucine Van Rechem, Jintai Chen, Tianfan Fu
Uncertainty Quantification Model Uncertainty Trial Outcome Prediction

December 28, 2023

Maintaining User Trust Through Multistage Uncertainty Aware Inference
Chandan Agrawal, Ashish Papanai, Jerome White
Scientific Inference Model Uncertainty User Trust AI Deployment Step Inference Stage Approach

December 18, 2023

Robust Active Measuring under Model Uncertainty
Merlijn Krale, Thiago D. Simão, Jana Tumova, Nils Jansen
Markov Decision Process Robust Version Model Uncertainty Sequential Decision Partial Observability

December 6, 2023

Bootstrap Your Own Variance
Polina Turishcheva, Jason Ramapuram, Sinead Williamson, Dan Busbridge, Eeshan Dhekane, Russ Webb
Contrastive Learning Model Uncertainty Bayesian Posterior Free Uncertainty

December 5, 2023

Role of Uncertainty in Anticipatory Trajectory Prediction for a Ping-Pong Playing Robot
Nima Rahmanian, Michael Gupta, Renzo Soatto, Srisai Nachuri, Michael Psenka, Yi Ma, S. Shankar Sastry
High Uncertainty Anticipation Integral Role Model Uncertainty Table Tennis Robot Interaction

December 1, 2023

Consensus group decision making under model uncertainty with a view towards environmental policy making
Phoebe Koundouri, Georgios I. Papayiannis, Electra V. Petracou, Athanasios N. Yannacopoulos
Model Uncertainty Consensus Group Decision Best View Barycenter Driven Localization

November 28, 2023

A personalized Uncertainty Quantification framework for patient survival models: estimating individual uncertainty of patients with metastatic brain tumors in the absence of ground truth
Yuqi Wang, Aarzu Gupta, David Carpenter, Trey Mullikin, Zachary J. Reitman, Scott Floyd, John Kirkpatrick, Joseph K. Salama, Paul W. Sperduto, Jian-Guo Liu, Mustafa R. Bashir, Kyle J. Lafata
Model Uncertainty Patient Friendly Language Brain Metastasis Stereotactic Body Radiation Therapy

November 20, 2023

Uncertainty Estimation in Contrast-Enhanced MR Image Translation with Multi-Axis Fusion
Ivo M. Baltruschat, Parvaneh Janbakhshi, Melanie Dohmen, Matthias Lenga
Uncertainty Estimation Model Uncertainty Volumetric Data

Model Uncertainty

Papers

Constrained Reinforcement Learning Under Model Mismatch

Error-Driven Uncertainty Aware Training

Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks

R2D2 image reconstruction with model uncertainty quantification in radio astronomy

Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process

Model Uncertainty in Evolutionary Optimization and Bayesian Optimization: A Comparative Analysis

Uncertainty Quantification for cross-subject Motor Imagery classification

Providing Safety Assurances for Systems with Unknown Dynamics

Uncertainty-Aware Evaluation for Vision-Language Models

OneBit: Towards Extremely Low-bit Large Language Models

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

Uncertainty Quantification on Clinical Trial Outcome Prediction

Maintaining User Trust Through Multistage Uncertainty Aware Inference

Robust Active Measuring under Model Uncertainty

Bootstrap Your Own Variance

Role of Uncertainty in Anticipatory Trajectory Prediction for a Ping-Pong Playing Robot

Consensus group decision making under model uncertainty with a view towards environmental policy making

A personalized Uncertainty Quantification framework for patient survival models: estimating individual uncertainty of patients with metastatic brain tumors in the absence of ground truth

Uncertainty Estimation in Contrast-Enhanced MR Image Translation with Multi-Axis Fusion