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.

When Belief Functions and Lower Probabilities are Indistinguishable / E.A. Corsi, T. Flaminio, H. Hosni (PROCEEDINGS OF MACHINE LEARNING RESEARCH). - In: ISIPTA 2021[s.l] : Proceedings of Machine Learning Research, 2021. - pp. 83-89

When Belief Functions and Lower Probabilities are Indistinguishable

E.A. Corsi;H. Hosni
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.
Belief functions; coherence; geometric interpretation; imprecise probabilities; lower probabilities; uncertain reasoning
Settore M-FIL/02 - Logica e Filosofia della Scienza
Settore MAT/01 - Logica Matematica
Dipartimenti di Eccellenza 2018-2022 - Dipartimento di FILOSOFIA
https://leo.ugr.es/isipta21/pmlr/corsi21.pdf
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Corsi, Flaminio, Hosni - 2021 - When Belief Functions and Lower Probabilities are Indistinguishable(2).pdf

accesso aperto

Descrizione: Articolo
Tipologia: Publisher's version/PDF
Dimensione 150.89 kB
Formato Adobe PDF
150.89 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/856476
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact