Interacting reinforced urn systems


Statistical learning
MOX 23
Interacting reinforced urn systems
Monday 23rd June 2003
Paganoni, Anna Maria; Secchi Piercesare
Download link:
We introduce a class of a discrete time stochastic processes generated by interacting systems of reinforced urns. We show that such processes are asymptotically partially exchangeable and we prove a strong law of large numbers. Examples and the analysis of particular cases show that interacting reinforced urn systems are very flexible representations for modelling countable collections of dependents and asymptotically exchangeable sequences of random variables. First published in: Advances in Applied Probability - Vol. 36 No.3 (September 2004) by The Applied Probability Trust.
This report, or a modified version of it, has been also submitted to, or published on
A.M. Paganoni, P.Secchi (2004), Interacting reinforced urn systems, Advances in Applied Probability, 36, 791-804