Concentration inequalities and laws of large numbers under epistemic and regular irrelevance


Autoria(s): COZMAN, Fabio Gagliardi
Contribuinte(s)

UNIVERSIDADE DE SÃO PAULO

Data(s)

18/10/2012

18/10/2012

2010

Resumo

This paper presents concentration inequalities and laws of large numbers under weak assumptions of irrelevance that are expressed using lower and upper expectations. The results build upon De Cooman and Miranda`s recent inequalities and laws of large numbers. The proofs indicate connections between the theory of martingales and concepts of epistemic and regular irrelevance. (C) 2010 Elsevier Inc. All rights reserved.

Identificador

INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, v.51, n.9, Special Issue, p.1069-1084, 2010

0888-613X

http://producao.usp.br/handle/BDPI/18319

10.1016/j.ijar.2010.08.009

http://dx.doi.org/10.1016/j.ijar.2010.08.009

Idioma(s)

eng

Publicador

ELSEVIER SCIENCE INC

Relação

International Journal of Approximate Reasoning

Direitos

restrictedAccess

Copyright ELSEVIER SCIENCE INC

Palavras-Chave #Laws of large numbers #Lower and upper expectations and probabilities #Irrelevance and independence #RANDOM-VARIABLES #PROBABILITY #WEAK #Computer Science, Artificial Intelligence
Tipo

article

proceedings paper

publishedVersion