Computing lower and upper expectations under epistemic independence

Cassio Polpo de Campos, Fábio Gagliardi Cozman

Abstract: This paper investigates the computation of lower/upper expectations that must cohere with a collection of probabilistic assessments and a collection of judgements of epistemic independence. New algorithms, based on multilinear programming, are presented, both for independence among events and among random variables. Separation properties of graphical models are also investigated.