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

October 30, 2023

Model Uncertainty based Active Learning on Tabular Data using Boosted Trees
Sharath M Shankaranarayana
Active Learning Tabular Data Model Uncertainty Boosted Tree

October 19, 2023

A Deep Learning Analysis of Climate Change, Innovation, and Uncertainty
Michael Barnett, William Brock, Lars Peter Hansen, Ruimeng Hu, Joseph Huang
High Uncertainty Anticipation Model Uncertainty Digital Innovation Climate Change Atmospheric Dynamic Climate Economic

October 4, 2023

Assessment of Prediction Intervals Using Uncertainty Characteristics Curves
Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri
Direct Assessment Model Uncertainty Prediction Interval Uncertainty Expression

October 3, 2023

Distributionally Safe Reinforcement Learning under Model Uncertainty: A Single-Level Approach by Differentiable Convex Programming
Alaa Eddine Chriat, Chuangchuang Sun
Reinforcement Learning Model Uncertainty Safety Constraint Single Stage Differentiable Convex

September 16, 2023

DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning
Xiao-Yin Liu, Xiao-Hu Zhou, Xiao-Liang Xie, Shi-Qi Liu, Zhen-Qiu Feng, Hao Li, Mei-Jiang Gui, Tian-Yu Xiang, De-Xing Huang, Zeng-Guang Hou
Reinforcement Learning Model Based Reinforcement Learning Model Uncertainty Internet Service Domain Model Based Offline Reinforcement Learning

September 6, 2023

On the Impact of Feeding Cost Risk in Aquaculture Valuation and Decision Making
Christian Oliver Ewald, Kevin Kamm
Global Impact Decision Making Model Uncertainty Aquaculture System Stochastic Behavior

August 8, 2023

ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems
Harry Li, Steven Jorgensen, John Holodnak, Allan Wollaber
Model Uncertainty Class Probability Uncertainty Visualization Uncertainty Aware Deep Learning Uncertainty Estimation Performance

August 6, 2023

Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing
Shuang Ao
Artificial Intelligence Uncertainty Quantification Model Uncertainty Accurate Uncertainty System Safety Safety Critical Task

July 5, 2023

A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
Atul Agrawal, Phaedon-Stelios Koutsourelakis
Model Uncertainty Aleatoric Uncertainty Closure Model Non Gaussian Aleatoric Uncertainty Reynolds Averaged Navier Stokes Reynolds Stress

July 2, 2023

Data-Driven Probabilistic Energy Consumption Estimation for Battery Electric Vehicles with Model Uncertainty
Ayan Maity, Sudeshna Sarkar
Model Uncertainty Energy Prediction Vehicle Energy Consumption

June 23, 2023

Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation
Marcel Matha, Christian Morsbach
Random Forest Epistemic Uncertainty Model Uncertainty High Uncertainty Value Prediction Confidence Turbulence Model Process Simulation

June 9, 2023

June 1, 2023

Quantifying Deep Learning Model Uncertainty in Conformal Prediction
Hamed Karimi, Reza Samavi
Uncertainty Quantification Conformal Prediction Predictive Uncertainty Model Uncertainty Computational Uncertainty Deep Learning Model Uncertainty

May 25, 2023

Gaussian Processes with State-Dependent Noise for Stochastic Control
Marcel Menner, Karl Berntorp
Gaussian Process Model Uncertainty Stochastic Control Dependent Noise

May 18, 2023

Bayesian Risk-Averse Q-Learning with Streaming Observations
Yuhao Wang, Enlu Zhou
Optimal Policy Model Uncertainty Robust Reinforcement Learning Risk Averse Reinforcement Learning

May 1, 2023

Variational Inference for Bayesian Neural Networks under Model and Parameter Uncertainty
Aliaksandr Hubin, Geir Storvik
Full Model Variational Inference Bayesian Neural Network Model Uncertainty Structure Learning Parameter Uncertainty Scalable Variational Scalable Bayesian

April 12, 2023

Communicating Uncertainty in Machine Learning Explanations: A Visualization Analytics Approach for Predictive Process Monitoring
Nijat Mehdiyev, Maxim Majlatow, Peter Fettke
Uncertainty Quantification Model Uncertainty Explainable Machine Learning Visual Analytics Predictive Process Monitoring

March 29, 2023

ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation
Wei Wei, Jiahuan Zhou, Hongze Li, Ying Wu
Model Uncertainty Uncertainty Aware Data Uncertainty Uncertainty Modeling Adversarial Uncertainty

February 26, 2023

A Comprehensive Survey on Uncertainty Quantification for Deep Learning
Wenchong He, Zhe Jiang
Deep Learning Deep Neural Network Uncertainty Quantification Comprehensive Survey Model Uncertainty Data Uncertainty DNN Prediction