paper-with-me

홈 › Papers

Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals

2021-06-01 · Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri

Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI. In regression tasks, uncertainty is typically quantified using prediction intervals calibrated to a specific operating point, making evaluation and comparison across different studies difficult. Our work leverages: (1) the concept of operating characteristics curves and (2) the notion of a gain over a simple reference, to derive a novel operating point agnostic assessment methodology for prediction intervals. The paper describes the corresponding algorithm, provides a theoretical analysis, and demonstrates its utility in multiple scenarios. We argue that the proposed method addresses the current need for comprehensive assessment of prediction intervals and thus represents a valuable addition to the uncertainty quantification toolbox.

📄 PDF Abstract BibTeX arXiv:2106.00858

Code (1)

IBM/UQ360 pytorch

Tasks

PredictionPrediction IntervalsregressionUncertainty Quantification

Similar Papers 제목 키워드 기반

Assessment of Prediction Intervals Using Uncertainty Characteristics Curves

2023-10-04 · Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh 외

Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI. In regression tasks, uncertainty is typically quantified using prediction intervals calibrated to an ad-h…

PredictionPrediction IntervalsUncertainty Quantification

Towards Uncertainty Quantification in Generative Model Learning

2025-11-13 · Giorgio Morales, Frederic Jurie, Jalal Fadili arxiv

While generative models have become increasingly prevalent across various domains, fundamental concerns regarding their reliability persist. A crucial yet understudied aspect of these models is the uncertainty quantifica…

Conformal Prediction on Quantifying Uncertainty of Dynamic Systems

2024-12-12 · Aoming Liang, Qi Liu, Lei Xu, Fahad Sohrab 외

Numerous studies have focused on learning and understanding the dynamics of physical systems from video data, such as spatial intelligence. Artificial intelligence requires quantitative assessments of the uncertainty of …

Conformal PredictionOperator learningPredictionTime Series

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment

2026-02-17 · Hang Li, Kaiqi Yang, Xianxuan Long, Fedor Filippov 외 arxiv

The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptability to diverse question types and flexibi…

Conditional Prediction ROC Bands for Graph Classification

2024-10-20 · Yujia Wu, Bo Yang, Elynn Chen, Yuzhou Chen 외

Graph classification in medical imaging and drug discovery requires accuracy and robust uncertainty quantification. To address this need, we introduce Conditional Prediction ROC (CP-ROC) bands, offering uncertainty quant…

ClassificationDrug DiscoveryGraph ClassificationPrediction+1