Title :
An inverse of Sanov´s theorem
Author :
Ganesh, A.J. ; O´Connell, Neil
Author_Institution :
BRIMS, Hewlett-Packard Labs., Bristol, UK
Abstract :
Let (Xk)k⩾1 be a sequence of independent, identically distributed random variables taking values in a finite set, and consider the problem of estimating the law of X1 in a Bayesian framework. We prove that the sequence of posterior distributions satisfies a large deviation principle, and give an explicit expression for the rate function. We extend the result to Bayesian inference on compact metric spaces using Dirichlet process priors
Keywords :
Bayes methods; inverse problems; random processes; sequences; Bayesian inference; Dirichlet process priors; Sanov´s theorem; compact metric spaces; finite set; identically distributed random variables; inverse inference; large deviation principle; law; posterior distributions; rate function; sequence; Bayesian methods; Entropy; Extraterrestrial measurements; Probability; Random sequences; Random variables; Statistical distributions; Topology;
Conference_Titel :
Information Theory, 1998. Proceedings. 1998 IEEE International Symposium on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-7803-5000-6
DOI :
10.1109/ISIT.1998.709018
