Computable de Finetti measures
Logic
2012-02-03 v2 Logic in Computer Science
Programming Languages
Probability
Statistics Theory
Machine Learning
Statistics Theory
Abstract
We prove a computable version of de Finetti's theorem on exchangeable sequences of real random variables. As a consequence, exchangeable stochastic processes expressed in probabilistic functional programming languages can be automatically rewritten as procedures that do not modify non-local state. Along the way, we prove that a distribution on the unit interval is computable if and only if its moments are uniformly computable.
Cite
@article{arxiv.0912.1072,
title = {Computable de Finetti measures},
author = {Cameron E. Freer and Daniel M. Roy},
journal= {arXiv preprint arXiv:0912.1072},
year = {2012}
}
Comments
32 pages. Final journal version; expanded somewhat, with minor corrections. To appear in Annals of Pure and Applied Logic. Extended abstract appeared in Proceedings of CiE '09, LNCS 5635, pp. 218-231