Effective Bayesian Inference for Stochastic Programs
Daphne Koller, David McAllester, Avi Pfeffer · 1997
In this paper, we propose a stochastic version of a general purpose functional programming language as a method of modeling stochastic processes. The language contains random choices, conditional statements, structured values, defined functions, and recursion. By imagining an experiment in which the program is "run" and the random choices made by sampling, we can interpret a program in this language as encoding a probability distribution over a (potentially infinite) set of objects. We provide an exact algorithm for computing conditional probabilities of the form Pr(P (x) j Q(x)) where x is chosen randomly from this distribution. This algorithm terminates precisely when sampling x and computing P (x) and Q(x) terminates in all possible stochastic executions (under lazy evaluation semantics, in which only values needed to compute the output of the program are evaluated) . We demonstrate the applicability of the languageand the efficiency of the inference algorithm by encoding both Bay...
Cited by 89 works.
Authors
References
- Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
- An introduction to hidden Markov models
- Statistical Language Learning
- A model for reasoning about persistence and causation
- Applications of stochastic context-free grammars using the Inside-Outside algorithm
- Probabilistic Horn abduction and Bayesian networks
- Probabilistic Independence Networks for Hidden Markov Probability Models
- Context-Specific Independence in Bayesian Networks
- Bucket Elimination: A Unifying Framework for Probabilistic Inference
- Planning with deadlines in stochastic domains