Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators

Deconstructing model reliability through advanced statistical estimation techniques.

We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverages recent advances in approxim...

ArXiv CS.LG2026-08-11