We use imprecise probabilities, based on a concept of generalized coherence, for the management of uncertainty in Artificial Intelligence. With the aim of reducing the computational difficulties, in the checking of generalized coherence we propose a method which exploits, in the framework of the betting criterion, suitable subsets of the sets of values of the random gains. We give an algorithm in each step of which a linear system with a reduced number of unknowns can be used. Our method improves a procedure already existing in literature and could be integrated with recent approaches of other authors, who exploit suitable logical conditions with the aim of splitting the problem into subproblems. We remark that our approach could be also used in combination with efficient methods like column generation techniques. Finally, to illustrate our method, we give some examples.

On the linear structure of betting criterion and the checking of coherence

BIAZZO, Veronica;
2002-01-01

Abstract

We use imprecise probabilities, based on a concept of generalized coherence, for the management of uncertainty in Artificial Intelligence. With the aim of reducing the computational difficulties, in the checking of generalized coherence we propose a method which exploits, in the framework of the betting criterion, suitable subsets of the sets of values of the random gains. We give an algorithm in each step of which a linear system with a reduced number of unknowns can be used. Our method improves a procedure already existing in literature and could be integrated with recent approaches of other authors, who exploit suitable logical conditions with the aim of splitting the problem into subproblems. We remark that our approach could be also used in combination with efficient methods like column generation techniques. Finally, to illustrate our method, we give some examples.
2002
conditional probability bounds; basic sets; algorithms
File in questo prodotto:
File Dimensione Formato  
AMAI-RM.pdf

solo gestori archivio

Tipologia: Documento in Pre-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 185.01 kB
Formato Adobe PDF
185.01 kB Adobe PDF   Visualizza/Apri

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/20.500.11769/41032
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact