paper-with-me

Papers

Uncertainty Quantification for Machine Learning: One Size Does Not Fit All

2025-12-13 · Paul Hofman, Yusuf Sale, Eyke Hüllermeier arxiv

Proper quantification of predictive uncertainty is essential for the use of machine learning in safety-critical applications. Various uncertainty measures have been proposed for this purpose, typically claiming superiority over other measures. In this paper, we argue that there is no single best measure. Instead, uncertainty quantification should be tailored to the specific application. To this end, we use a flexible family of uncertainty measures that distinguishes between total, aleatoric, and epistemic uncertainty of second-order distributions. These measures can be instantiated with specific loss functions, so-called proper scoring rules, to control their characteristics, and we show that different characteristics are useful for different tasks. In particular, we show that, for the task of selective prediction, the scoring rule should ideally match the task loss. On the other hand, for out-of-distribution detection, our results confirm that mutual information, a widely used measure of epistemic uncertainty, performs best. Furthermore, in an active learning setting, epistemic uncertainty based on zero-one loss is shown to consistently outperform other uncertainty measures.

📄 PDF Abstract BibTeX arXiv:2512.12341

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution DetectionActive Learning

Similar Papers 제목 키워드 기반

Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning

2025-07-20 · Maximilian Wendlinger, Kilian Tscharke, Pascal Debus arxiv

One of the key obstacles in traditional deep learning is the reduction in model transparency caused by increasingly intricate model functions, which can lead to problems such as overfitting and excessive confidence in pr…

Quantum Machine Learning

Uncertainty Quantification for Transformer Models for Dark-Pattern Detection

2024-12-06 · Javier Muñoz, Álvaro Huertas-García, Carlos Martí-González, Enrique De Miguel Ambite

The opaque nature of transformer-based models, particularly in applications susceptible to unethical practices such as dark-patterns in user interfaces, requires models that integrate uncertainty quantification to enhanc…

Gaussian ProcessesUncertainty Quantification

Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs

2022-08-02 · Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco 외

Neural operators are a type of deep architecture that learns to solve (i.e. learns the nonlinear solution operator of) partial differential equations (PDEs). The current state of the art for these models does not provide…

Gaussian ProcessesUncertainty Quantification

Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation

2022-03-11 · Viktor Bengs, Eyke Hüllermeier, Willem Waegeman

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latt…

Uncertainty Quantification

Uncertainty quantification for improving radiomic-based models in radiation pneumonitis prediction

2024-12-27 · Chanon Puttanawarut, Romen Samuel Wabina, Nat Sirirutbunkajorn

Background: Radiation pneumonitis is a side effect of thoracic radiation therapy. Recently, machine learning models with radiomic features have improved radiation pneumonitis prediction by capturing spatial information. …

Conformal PredictionDecision MakingPredictionregression+1