Variational Program Inference

Details Variational Program Inference Variational Program Inference

2010-06-04

arxiv.org/abs/1006.0991v1

Computer Science

Artificial Intelligence

Scientific paper

We introduce a framework for representing a variety of interesting problems as inference over the execution of probabilistic model programs. We represent a "solution" to such a problem as a guide program which runs alongside the model program and influences the model program's random choices, leading the model program to sample from a different distribution than from its priors. Ideally the guide program influences the model program to sample from the posteriors given the evidence. We show how the KL- divergence between the true posterior distribution and the distribution induced by the guided model program can be efficiently estimated (up to an additive constant) by sampling multiple executions of the guided model program. In addition, we show how to use the guide program as a proposal distribution in importance sampling to statistically prove lower bounds on the probability of the evidence and on the probability of a hypothesis and the evidence. We can use the quotient of these two bounds as an estimate of the conditional probability of the hypothesis given the evidence. We thus turn the inference problem into a heuristic search for better guide programs.

Affiliated with

Also associated with

No associations

Rating

Variational Program Inference does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Variational Program Inference, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Variational Program Inference will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-637848