Bayesian Uncertainty

Bayesian uncertainty quantification aims to provide reliable estimates of the uncertainty associated with predictions from machine learning models, improving the trustworthiness and robustness of these models. Current research focuses on improving the calibration and utility of uncertainty estimates, particularly within deep learning architectures like Bayesian neural networks and normalizing flows, often employing techniques such as Hamiltonian Monte Carlo sampling and stochastic weight averaging. This work is crucial for applications where reliable uncertainty quantification is essential, such as medical image analysis, drug discovery, and safety-critical systems, enabling more informed decision-making and reducing the risk of "silent failures."

Papers

September 5, 2024

Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
Prerak Mody, Nicolas F. Chaves-de-Plaza, Chinmay Rao, Eleftheria Astrenidou, Mischa de Ridder, Nienke Hoekstra, Klaus Hildebrandt, Marius Staring
Bayesian Uncertainty Structural Uncertainty Deep Uncertainty Voxel Scale Uncertainty

August 1, 2024

Calibrating Bayesian Generative Machine Learning for Bayesiamplification
Sebastian Bieringer, Sascha Diefenbacher, Gregor Kasieczka, Mathias Trabs
Generative Modeling Bayesian Perspective Bayes Rule Bayesian Uncertainty Distributional Uncertainty Mean Field Variational

July 19, 2024

Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Models
Hannah Rosa Friesacher, Ola Engkvist, Lewis Mervin, Yves Moreau, Adam Arany
Decision Making Drug Discovery Neural Topic Drug Discovery Process Bayesian Uncertainty Bayesian Regression Probability Calibration Activity Based

June 7, 2024

Linearization Turns Neural Operators into Function-Valued Gaussian Processes
Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig
Gaussian Process Neural Operator Fourier Neural Operator Reverse Graph Linearization Bayesian Uncertainty

June 4, 2024

Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs
Filippo Valdettaro, A. Aldo Faisal
Reinforcement Learning Markov Decision Process Bayesian Optimisation Bayesian Uncertainty Epistemic Uncertainty Quantification

March 4, 2024

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation
Yidong Zhao, Joao Tourais, Iain Pierce, Christian Nitsche, Thomas A. Treibel, Sebastian Weingärtner, Artur M. Schweidtmann, Qian Tao
Financial Application Medical Image Segmentation Task Hamiltonian Monte Carlo Bayesian Uncertainty Segmentation Uncertainty Deep Learning Based Medical Bayesian Deep Deep Bayesian

February 6, 2024

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
Idan Achituve, Idit Diamant, Arnon Netzer, Gal Chechik, Ethan Fetaya
Multi Task Learning Natural Gradient Bayesian Inference Inference Task Bayesian Uncertainty Aggregated Gradient Gradient Aggregation

December 23, 2023

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Gianni Franchi, Olivier Laurent, Maxence Leguéry, Andrei Bursuc, Andrea Pilzer, Angela Yao
Deep Neural Network Pre Trained Model Bayesian Neural Network Simple Strategy Bayesian Uncertainty

December 13, 2023

Estimation of Concept Explanations Should be Uncertainty Aware
Vihari Piratla, Juyeon Heo, Katherine M. Collins, Sukriti Singh, Adrian Weller
Estimation Task Model Explanation Bayesian Uncertainty Model Understanding Concept Explanation Uncertainty Awareness

November 18, 2023

On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Duy Minh Ho Nguyen, Tan Ngoc Pham, Nghiem Tuong Diep, Nghi Quoc Phan, Quang Pham, Vinh Tong, Binh T. Nguyen, Ngan Hoang Le, Nhat Ho, Pengtao Xie, Daniel Sonntag, Mathias Niepert
Foundation Model Medical Image Segmentation Robust Model Pre Trained Convolutional Neural Network Bayesian Uncertainty

October 29, 2023

Out-of-distribution Object Detection through Bayesian Uncertainty Estimation
Tianhao Zhang, Shenglin Wang, Nidhal Bouaynaya, Radu Calinescu, Lyudmila Mihaylova
Object Detection Distribution Detection Object Detector Bayesian Uncertainty Distribution Object Distribution Identification

July 10, 2023

Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data
Ziyu Xie, Mahmoud Yaseen, Xu Wu
Deeper Network Bayesian Uncertainty Functional Principal Component Transient Imaging Data Clad Characteristic Inverse UQ

June 6, 2023

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression
Youngsoo Baek, Samuel I. Berchuck, Sayan Mukherjee
Posterior Predictive Asymptotic Behavior Bayesian Uncertainty Bayesian Model Averaging Random Feature Regression Posteriori Error

May 26, 2023

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng
Large Language Model Machine Generated High Detection Efficient Detection LLM Generated Text Probabilistic Surrogate Bayesian Uncertainty

April 10, 2023

Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging
Aarne Talman, Hande Celikkanat, Sami Virpioja, Markus Heinonen, Jörg Tiedemann
Language Understanding Natural Language Inference Bayesian Uncertainty Stochastic Weight Averaging Uncertainty Representation

March 6, 2023

Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification
Rafael Orozco, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Tristan van Leeuwen, Felix Herrmann
Uncertainty Quantification Normalizing Flow Bayesian Uncertainty Reconstruction Uncertainty Transcranial Ultrasound

February 17, 2023

Bayesian Quantification with Black-Box Estimators
Albert Ziegler, Paweł Czyż
Black Box Cross View Probabilistic Classifier Class Distribution Bayesian Uncertainty

December 12, 2022

Efficient Bayesian Uncertainty Estimation for nnU-Net
Yidong Zhao, Changchun Yang, Artur Schweidtmann, Qian Tao
Medical Image Segmentation Multi Modal Posterior Sampling Bayesian Uncertainty nnU Net

September 14, 2022

Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications
Somrita Banerjee, Apoorva Sharma, Edward Schmerling, Max Spolaor, Michael Nemerouf, Marco Pavone
Active Learning Learning Based Model Performance Model Retraining Bayesian Uncertainty Data Management Input Distribution

February 7, 2022

Theoretical characterization of uncertainty in high-dimensional linear classification
Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
Ground Truth High Uncertainty Anticipation Dimensional Input Bayes Classifier Bayesian Uncertainty Heuristic Estimate

Bayesian Uncertainty

Papers

Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation

Calibrating Bayesian Generative Machine Learning for Bayesiamplification

Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Models

Linearization Turns Neural Operators into Function-Valued Gaussian Processes

Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

Estimation of Concept Explanations Should be Uncertainty Aware

On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation

Out-of-distribution Object Detection through Bayesian Uncertainty Estimation

Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model

Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging

Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification

Bayesian Quantification with Black-Box Estimators

Efficient Bayesian Uncertainty Estimation for nnU-Net

Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications

Theoretical characterization of uncertainty in high-dimensional linear classification