Year: 2025
Type: preprint
Abstract: 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. In this work, we propose an intuitive framework for uncertainty estimation and decomposition based on the signal-to-noise ratio of class probability distributions across different model predictions. We introduce a variance-gated measure that scales predictions by a confidence factor derived from ensembles. We use this measure to discuss the existence of a collapse in the diversity of committee machines.
Source: arXiv (Cornell University)
Institution: Dalhousie University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7081570942
Cites:
Cited by:
Related to: