Toward general analysis of recursive probability models

  • Authors:

  • Daniel Pless;George Luger

  • Affiliations:

  • Computer Science Department, University of New Mexico, Albuquerque, NM;Computer Science Department, University of New Mexico, Albuquerque, NM

  • Venue:
  • UAI'01 Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

There is increasing interest within the research community in the design and use of recursive probability models. There remains concern about computational complexity costs and the fact that computing exact solutions can be intractable for many nonrecursive models. Although inference is undecidable in the general case for recursive problems, several research groups are actively developing computational techniques for recursive stochastic languages. We have developed an extension to the traditional λ calculus as a framework for families of Turing complete stochastic languages. We have also developed a class of exact inference algorithms based on the traditional reductions of the λ calculus. We further propose that using the deBruijn notation (a λ-calculus notation with nameless dummies) supports effective caching in such systems, as the reuse of partial solutions is an essential component of efficient computation. Finally, our extension to the λ-calculus offers a foundation and general theory for the construction of recursive stochastic modeling languages as well as promise for effective caching and efficient approximation algorithms for inference.