Computable Exchangeable Sequences Have Computable de Finetti Measures

  • Authors:
  • Cameron E. Freer;Daniel M. Roy

  • Affiliations:
  • Department of Mathematics, Massachusetts Institute of Technology,;Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology,

  • Venue:
  • CiE '09 Proceedings of the 5th Conference on Computability in Europe: Mathematical Theory and Computational Practice
  • Year:
  • 2009

Quantified Score

Hi-index 0.02

Visualization

Abstract

We prove a uniformly computable version of de Finetti's theorem on exchangeable sequences of real random variables. In the process, we develop machinery for computably recovering a distribution from its sequence of moments, which suffices to prove the theorem in the case of (almost surely) continuous directing random measures. In the general case, we give a proof inspired by a randomized algorithm which succeeds with probability one. Finally, we show how, as a consequence of the main theorem, exchangeable stochastic processes in probabilistic functional programming languages can be rewritten as procedures that do not use mutation.