← Search

Sebastian Gruber

2 accepted papers

2023

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

AISTATS 2023poster

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 is via the predicted confidence. While this tends to work well for in-domain samples, these estimates are unreliable und…

2021

Post-Hoc Uncertainty Calibration for Domain Drift Scenarios

CVPR 2021poster

We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representative of the true likelihood of a prediction can be achieved using post-hoc calibration methods. However, to date, the focus…

Cited by 89PDFcodeScholar