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 13, 2024

Voxeland: Probabilistic Instance-Aware Semantic Mapping with Evidence-based Uncertainty Quantification
Jose-Luis Matez-Bandera, Pepe Ojeda, Javier Monroy, Javier Gonzalez-Jimenez, Jose-Raul Ruiz-Sarmiento
Uncertainty Quantification Scene Understanding Semantic Uncertainty

November 12, 2024

MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Data
Chika Maduabuchi, Ericmoore Jossou, Matteo Bucci
Convolutional Neural Network Uncertainty Quantification Segmentation Model Segmentation Result Segmentation Accuracy Phase Recognition Multimodal Segmentation

November 11, 2024

Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification
Jannik Franzen, Claudia Winklmayr, Vanessa E. Guarino, Christoph Karg, Xiaoyan Yu, Nora Koreuber, Jan P. Albrecht, Philip Bischoff, Dagmar Kainmueller
Uncertainty Quantification Controllability Condition Histopathology Datasets Reliable Segmentation Segmentation Problem Internal Noise

November 9, 2024

UQ of 2D Slab Burner DNS: Surrogates, Uncertainty Propagation, and Parameter Calibration
Georgios Georgalis, Alejandro Becerra, Kenneth Budzinski, Matthew McGurn, Danial Faghihi, Paul E. DesJardin, Abani Patra
Uncertainty Quantification 2 Dimensional Model Calibration Uncertainty Propagation Parameter Uncertainty Surrogate Assisted Version Data Driven Surrogate Fuel Consumption Combustion System Uncertainty Quantification Method

November 5, 2024

Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models
Zizhang Chen, Peizhao Li, Xiaomeng Dong, Pengyu Hong
Language Model Uncertainty Quantification Model Uncertainty Clinical Prediction Task Clinical Outcome Prediction

November 4, 2024

November 3, 2024

Strategic Conformal Prediction
Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert
Native Robustness Uncertainty Quantification Conformal Prediction Theoretical Guarantee Conformal Prediction Region

October 30, 2024

October 29, 2024

Uncertainty Quantification via Hölder Divergence for Multi-View Representation Learning
an Zhang, Ming Li, Chun Li, Zhaoxia Liu, Ye Zhang, Fei Richard Yu
Representation Learning Uncertainty Quantification Multi View Robust Version Kullback Leibler Divergence Prediction Uncertainty Dempster Shafer Theory Inherent Uncertainty

October 28, 2024

CODES: Benchmarking Coupled ODE Surrogates
Robin Janssen, Immanuel Sulzer, Tobias Buck
Uncertainty Quantification Parallel Training Code Data Baseline Model Surrogate Assisted Version

October 27, 2024

Integrating uncertainty quantification into randomized smoothing based robustness guarantees
Sina Däubener, Kira Maag, David Krueger, Asja Fischer
Adversarial Attack Native Robustness Uncertainty Quantification Robustness Evaluation Robustness Guarantee Smoothing Factor

October 24, 2024

Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation
Hai Siong Tan, Kuancheng Wang, Rafe Mcbeth
Uncertainty Quantification Evidential Deep Learning Biomedical Image Segmentation

October 20, 2024

Conditional Uncertainty Quantification for Tensorized Topological Neural Networks
Yujia Wu, Bo Yang, Yang Zhao, Elynn Chen, Yuzhou Chen, Zheshi Zheng
Graph Neural Network Uncertainty Quantification Network Programming Tensor Decomposition Prediction Uncertainty

Uncertainty Quantification

Papers

Voxeland: Probabilistic Instance-Aware Semantic Mapping with Evidence-based Uncertainty Quantification

MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Data

Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification

UQ of 2D Slab Burner DNS: Surrogates, Uncertainty Propagation, and Parameter Calibration

Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI

Targeted Learning for Variable Importance

Strategic Conformal Prediction

Multi-fidelity Machine Learning for Uncertainty Quantification and Optimization

Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry

Legitimate ground-truth-free metrics for deep uncertainty classification scoring

Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings

Uncertainty Quantification via Hölder Divergence for Multi-View Representation Learning

CODES: Benchmarking Coupled ODE Surrogates

Integrating uncertainty quantification into randomized smoothing based robustness guarantees

Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation

Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification

The Probabilistic Tsetlin Machine: A Novel Approach to Uncertainty Quantification

Can Uncertainty Quantification Enable Better Learning-based Index Tuning?

Conditional Uncertainty Quantification for Tensorized Topological Neural Networks