---
title: Evidential Uncertainty in Deep Learning
url: https://www.emergentmind.com/topics/evidential-uncertainty-quantification
type: topic
---

# Evidential Uncertainty in Deep Learning

Evidential uncertainty quantification refers to a family of techniques, principally typified by the Evidential Deep Learning (EDL) framework, in which a neural network is trained to predict not just pointwise predictive probabilities or regression outputs, but a higher-order distribution over such predictions—termed a “meta-distribution” or “evidential distribution.” This permits the estimation of both aleatoric (data) and epistemic (model) uncertainty from a single deterministic forward pass, via outputting parameters of a conjugate prior (Dirichlet for classification, Normal–Inverse-Gamma for regression) instead of direct target estimates. The method’s computational efficiency and its formal decomposition of uncertainty make it attractive for downstream tasks including out-of-distribution (OOD) detection, selective classification, and robust scientific modeling. However, recent analyses have revealed critical limitations in its epistemic quantification, which have driven ongoing theoretical and empirical refinements [2402.06160].

## 1. Second-Order Uncertainty Modeling in Deep Learning

The essential innovation of evidential uncertainty quantification is to regard the neural network output as parametrizing a “second-order” meta-distribution. In classification with $C$ classes, instead of a softmax producing $p_\theta(y|x) \in \Delta^{C-1}$, the network outputs an evidence vector $e(x) \in \mathbb{R}^C_{\ge 0}$, used to define Dirichlet parameters $\alpha(x) = e(x) + 1$. The resulting Dirichlet distribution $\operatorname{Dir}(\theta; \alpha(x))$ models a distribution over possible class-probability vectors $\theta \in \Delta^{C-1}$, explicitly capturing

Source: https://www.emergentmind.com/topics/evidential-uncertainty-quantification