11 citations · 12 across the 2 of their papers we have counts for
3 papers
cs.LG2022★ 1 cited
Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition
Sebastian G. Gruber, Florian Buettner
Reliably estimating the uncertainty of a prediction throughout the model lifecycle is crucial in many safety-critical applications. The most common way to measure this uncertainty…
cs.LG2022★ 11 cited
Better Uncertainty Calibration via Proper Scores for Classification and Beyond
Sebastian G. Gruber, Florian Buettner
With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neura…
cs.LG2020
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem +2
We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representativ…