How to assess coherent beliefs: A comparison of different notions of coherence in Dempster-Shafer theory of evidence
Davide Petturiti, Barbara Vantaggi

TL;DR
This paper systematically compares different notions of coherence within Dempster-Shafer theory, demonstrating their equivalence and connecting them to probability theory to enhance understanding of belief assessment.
Contribution
It provides a comprehensive analysis of coherence notions in Dempster-Shafer theory, establishing their equivalence and linking them to classical probability concepts.
Findings
All coherence notions are shown to be equivalent within Dempster-Shafer theory.
The study clarifies the relationship between coherence and probability theory.
Results support unified frameworks for belief assessment in evidence theory.
Abstract
Stemming from de Finetti's work on finitely additive coherent probabilities, the paradigm of coherence has been applied to many uncertainty calculi in order to remove structural restrictions on the domain of the assessment. Three possible approaches to coherence are available: coherence as a consistency notion, coherence as fair betting scheme, and coherence in terms of penalty criterion. Due to its intimate connection with (finitely additive) probability theory, Dempster-Shafer theory allows notions of coherence in all the forms recalled above, presenting evident similarities with probability theory. In this chapter we present a systematic study of such coherence notions showing their equivalence.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Modeling and Causal Inference
