Uncertainty Estimation using Variance-Gated Distributions

ArXi:2509.08846v2 Announce Type: replace-cross Evaluation of per-sample uncertainty quantification from neural networks is essential for decision-making involving high-risk applications. A common approach is to use the predictive distribution from Bayesian or approximation models and decompose the corresponding predictive uncertainty into epistemic (model-related) and aleatoric (data-related) components. However, additive decomposition has recently been questioned.