English

Control-Data Separation and Logical Condition Propagation for Efficient Inference on Probabilistic Programs

Machine Learning 2023-10-02 v3 Programming Languages

Abstract

We present a novel sampling framework for probabilistic programs. The framework combines two recent ideas -- \emph{control-data separation} and \emph{logical condition propagation} -- in a nontrivial manner so that the two ideas boost the benefits of each other. We implemented our algorithm on top of Anglican. The experimental results demonstrate our algorithm's efficiency, especially for programs with while loops and rare observations.

Keywords

Cite

@article{arxiv.2101.01502,
  title  = {Control-Data Separation and Logical Condition Propagation for Efficient Inference on Probabilistic Programs},
  author = {Ichiro Hasuo and Yuichiro Oyabu and Clovis Eberhart and Kohei Suenaga and Kenta Cho and Shin-ya Katsumata},
  journal= {arXiv preprint arXiv:2101.01502},
  year   = {2023}
}
R2 v1 2026-06-23T21:47:42.443Z