Credal nets under epistemic irrelevance

TL;DR

This paper introduces a novel approach to credal nets using epistemic irrelevance instead of strong independence, enabling more flexible modeling of imprecise probabilities with a focus on desirable gambles.

Contribution

It proposes a new framework for credal nets based on epistemic irrelevance, expanding the theoretical foundation and practical modeling capabilities for imprecise probabilities.

Findings

Constructs global models from local uncertainty assessments

Demonstrates properties of the new credal net framework

Uses sets of desirable gambles for generality and expressiveness

Abstract

We present a new approach to credal nets, which are graphical models that generalise Bayesian nets to imprecise probability. Instead of applying the commonly used notion of strong independence, we replace it by the weaker notion of epistemic irrelevance. We show how assessments of epistemic irrelevance allow us to construct a global model out of given local uncertainty models and mention some useful properties. The main results and proofs are presented using the language of sets of desirable gambles, which provides a very general and expressive way of representing imprecise probability models.