AN URN MODEL FROM LEARNING-THEORY

Authors
BOUCHERON S GARDY D
Citation
S. Boucheron et D. Gardy, AN URN MODEL FROM LEARNING-THEORY, Random structures & algorithms, 10(1-2), 1997, pp. 43-67
Citations number
21
Categorie Soggetti
Mathematics,Mathematics,Mathematics,"Computer Science Software Graphycs Programming
Journal title
Random structures & algorithms → ACNP
ISSN journal
10429832
Volume
10
Issue
1-2
Year of publication
1997
Pages
43 - 67
Database
ISI
SICI code
1042-9832(1997)10:1-2<43:AUMFL>2.0.ZU;2-O
Abstract
We present an urn model that is a variation of the classical occupancy model, and in which the balls are of two types (good and bad). We ana lyze the number of urns that contain more (or fewer) good balls than b ad balls. We find Gaussian limiting distributions in the static case a nd convergence of the finite-dimensional distributions towards those o f a Gaussian, non-Markov process in the dynamic case. (C) 1997 John Wi ley & Sons, Inc.