Uncertainty Propagation

Uncertainty propagation focuses on accurately estimating the impact of input uncertainties on the outputs of complex systems, models, and algorithms. Current research emphasizes developing efficient and reliable methods for propagating uncertainty through various model architectures, including neural networks (e.g., Bayesian neural networks, Gaussian processes), and employing techniques like moment matching, polynomial chaos expansion, and conformal prediction. This field is crucial for enhancing the trustworthiness and reliability of AI-driven systems in safety-critical applications like aviation and autonomous vehicles, as well as improving the accuracy and robustness of scientific simulations and data analysis.

Papers

October 24, 2023

GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Tong He, Yonghui Li, Wanli Ouyang
3D Detection Monocular 3D Object Detection Uncertainty Propagation Perspective Projection Depth Estimation Error Geometric Uncertainty

October 16, 2023

Accurate Data-Driven Surrogates of Dynamical Systems for Forward Propagation of Uncertainty
Saibal De, Reese E. Jones, Hemanth Kolla
High Uncertainty Anticipation Dynamical System Surrogate Model Nonlinear Dynamic Backward Propagation Uncertainty Propagation Data Driven Surrogate Collocation Point Surrogate Dynamic

October 7, 2023

AirIMU: Learning Uncertainty Propagation for Inertial Odometry
Yuheng Qiu, Chen Wang, Can Xu, Yutian Chen, Xunfei Zhou, Youjie Xia, Sebastian Scherer
Inertial Measurement Unit Uncertainty Propagation Inertial Odometry

September 19, 2023

Monte-Carlo tree search with uncertainty propagation via optimal transport
Tuan Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard
Markov Decision Process Optimal Transport Monte Carlo Tree Search Uncertainty Propagation Operator Selection

April 3, 2023

Uncertainty Propagation in Node Classification
Zhao Xu, Carolin Lawrence, Ammar Shaker, Raman Siarheyeu
Node Classification Predictive Uncertainty Uncertainty Propagation

March 25, 2023

Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation
Sanbao Su, Songyang Han, Yiming Li, Zhili Zhang, Chen Feng, Caiwen Ding, Fei Miao
Uncertainty Quantification Multi Object Tracking Multiple Object Tracking Uncertainty Propagation Collaborative Object

March 22, 2023

Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation
Heng Yang, Marco Pavone
Keypoint Detection Object Pose Estimation Uncertainty Propagation Statistical Guarantee Initial Pose Sparse Keypoints Pose UnceRtainty

February 23, 2023

Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification
Qiongqiong Wang, Kong Aik Lee, Tianchi Liu
High Uncertainty Anticipation Estimation Task Speaker Verification Discriminant Analysis Uncertainty Propagation Speech Driven Posterior Covariance

February 9, 2023

Efficient Propagation of Uncertainty via Reordering Monte Carlo Samples
Danial Khatamsaz, Vahid Attari, Raymundo Arroyave, Douglas L. Allaire
High Uncertainty Anticipation Uncertainty Estimation Model Uncertainty Monte Carlo Uncertainty Propagation Fast Propagation Material Informatics Monte Carlo Simulation

February 1, 2023

Selective Uncertainty Propagation in Offline RL
Sanath Kumar Krishnamurthy, Tanmay Gangwani, Sumeet Katariya, Branislav Kveton, Shrey Modi, Anshuka Rangi
Offline Reinforcement Learning Distribution Shift Contextual Bandit Dynamic Programming Uncertainty Propagation Offline Policy Learning

January 12, 2023

Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components
Fabio Arnez, Huascar Espinoza, Ansgar Radermacher, François Terrier
Autonomous System Model Uncertainty Bayesian Deep Learning Uncertainty Propagation Autonomous Aerial Navigation Trustworthy Autonomous System

November 20, 2022

The Past Does Matter: Correlation of Subsequent States in Trajectory Predictions of Gaussian Process Models
Steffen Ridderbusch, Sina Ober-Blöbaum, Paul Goulart
Gaussian Process Trajectory Prediction State Space Model Total Correlation Uncertainty Propagation Trajectory Distribution Structured State Evolution

October 25, 2022

Combined Data and Deep Learning Model Uncertainties: An Application to the Measurement of Solid Fuel Regression Rate
Georgios Georgalis, Kolos Retfalvi, Paul E. DesJardin, Abani Patra
Application Proficiency Raw Data Measurement System Uncertainty Propagation Pixel Wise Uncertainty Nuclear Fuel Deep Learning Model Uncertainty

October 19, 2022

Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing
Georgios Rizos, Jenna Lawson, Simon Mitchell, Pranay Shah, Xin Wen, Cristina Banks-Leite, Robert Ewers, Bjoern W. Schuller
Bayesian Neural Network Epistemic Uncertainty Predictive Uncertainty Uncertainty Aware Uncertainty Propagation

October 5, 2022

Boundary-Aware Uncertainty for Feature Attribution Explainers
Davin Hill, Aria Masoomi, Max Torop, Sandesh Ghimire, Jennifer Dy
High Uncertainty Anticipation Black Box Decision Boundary Uncertainty Propagation Explanation Uncertainty Feature Attribution Explanation Unified Uncertainty

October 1, 2022

Solving Coupled Differential Equation Groups Using PINO-CDE
Wenhao Ding, Qing He, Hanghang Tong, Qingjing Wang, Ping Wang
Uncertainty Propagation Physic Informed Neural Operator Density Evolution Coupled Partial Differential Equation

September 26, 2022

Just-In-Time Learning for Operational Risk Assessment in Power Grids
Oliver Stover, Pranav Karve, Sankaran Mahadevan, Wenbo Chen, Haoruo Zhao, Mathieu Tanneau, Pascal Van Hentenryck
Real Time Power Grid Uncertainty Propagation Economic Dispatch Operational Risk Real Time Risk

September 15, 2022

Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach
Yue Yu, Rongzhi Zhang, Ran Xu, Jieyu Zhang, Jiaming Shen, Chao Zhang
Language Model Pre Trained Language Model Prompt Based Learning Uncertainty Propagation Start Active Learning

July 21, 2022

Data-Driven Stochastic AC-OPF using Gaussian Processes
Mile Mitrovic, Aleksandr Lukashevich, Petr Vorobev, Vladimir Terzija, Semen Budenny, Yury Maximov, Deepjyoti Deka
Gaussian Process Power System Optimal Power Flow Uncertainty Propagation Power Flow Economic Dispatch

April 1, 2022

DBCal: Density Based Calibration of classifier predictions for uncertainty quantification
Alex Hagen, Karl Pazdernik, Nicole LaHaye, Marjolein Oostrom
Machine Learning Uncertainty Quantification Class Imbalance Semantic Segmentation Network Binary Classifier Uncertainty Propagation