Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier +1
Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks…
cs.LG2024
SCOD: From Heuristics to Theory
Vojtech Franc, Jakub Paplham, Daniel Prusa
This paper addresses the problem of designing reliable prediction models that abstain from predictions when faced with uncertain or out-of-distribution samples - a recently propose…