𝔖 Bobbio Scriptorium
✦   LIBER   ✦

L∞ Metric Criteria for Convergence in Bayesian Recursive Inference Systems

✍ Scribed by Bruce M. Bennett; Rachel B. Cohen


Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
126 KB
Volume
23
Category
Article
ISSN
0196-8858

No coin nor oath required. For personal study only.

✦ Synopsis


Motivated by applications to probabilistic inference, we consider a sequence of probability measures, called ''conclusion measures,'' on a fixed space X. The sequence is generated recursively via conditional probability, driven by a sequence Ž of input measures rather than by a sequence of punctual data, as in Bayesian . statistical inference . The general problem is to give conditions on the input measures such that the sequence of conclusion measures converges weakly. We develop L ϱ -metric criteria defined recursively on the input measures, which are Ž . sufficient but not necessary for the sequence of conclusion measures to converge at a given rate. We discuss the applications of this to the ''directed convergence w x strategy'' introduced in 1 . Finally, we show that if the input measures satisfy the criteria, then the input sequence also converges at a comparable rate.