Publication Date:
2021
Citation:
When Belief Functions and Lower Probabilities are Indistinguishable / E.A. Corsi, T. Flaminio, H. Hosni (PROCEEDINGS OF MACHINE LEARNING RESEARCH). - In: International Symposium on Imprecise Probability: Theories and Applications / [a cura di] A. Cano, J. De Bock, E. Miranda, S. Moral. - [s.l] : Proceedings of Machine Learning Research, 2021. - pp. 83-89 (( Intervento presentato al 12. convegno ISIPTA tenutosi a virtuale nel 2021.
abstract:
This paper reports on a geometrical investigation of de Finetti’s Dutch Book method as an operational foundation for a wide range of generalisations of probability measures, including lower probabilities, necessity measures and belief functions. Our main result identifies a number of non-limiting circumstances under which de Finetti’s coherence fails to lift from less to more general models. In particular our result shows that rich enough sets of events exist such that the coherence criteria for belief functions and lower probability collapse.
IRIS type:
03 - Contributo in volume
Keywords:
Belief functions; coherence; geometric interpretation; imprecise probabilities; lower probabilities; uncertain reasoning
List of contributors:
E.A. Corsi, T. Flaminio, H. Hosni
Link to information sheet:
Book title:
International Symposium on Imprecise Probability: Theories and Applications