Paper ID: 2312.10469

One step closer to unbiased aleatoric uncertainty estimation

Wang Zhang, Ziwen Ma, Subhro Das, Tsui-Wei Weng, Alexandre Megretski, Luca Daniel, Lam M. Nguyen

Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making. In the deep learning field, the uncertainties are usually categorized into aleatoric (data) and epistemic (model) uncertainty. In this paper, we point out that the existing popular variance attenuation method highly overestimates aleatoric uncertainty. To address this issue, we propose a new estimation method by actively de-noising the observed data. By conducting a broad range of experiments, we demonstrate that our proposed approach provides a much closer approximation to the actual data uncertainty than the standard method.

Submitted: Dec 16, 2023