3 papers
cs.LG2026
Efficient Credal Prediction through Decalibration
Paul Hofman, Timo Löhr, Maximilian Muschalik +2
A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.…
stat.ML2025
Credal Prediction based on Relative Likelihood
Timo Löhr, Paul Hofman, Felix Mohr +1
Predictions in the form of sets of probability distributions, so-called credal sets, provide a suitable means to represent a learner's epistemic uncertainty. In this paper, we prop…
cs.LG2024
Label-wise Aleatoric and Epistemic Uncertainty Quantification
Yusuf Sale, Paul Hofman, Timo Löhr +3
We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows unce…