NeurIPS 2022accept3 citations
Rethinking Variational Inference for Probabilistic Programs with Stochastic Support
Tim Reichelt, Luke Ong, Tom Rainforth
Abstract
We introduce Support Decomposition Variational Inference (SDVI), a new variational inference (VI) approach for probabilistic programs with stochastic support. Existing approaches to this problem rely on designing a single global variational guide on a variable-by-variable basis, while maintaining the stochastic control flow of the original program. SDVI instead breaks the program down into sub-programs with static support, before automatically building separate sub-guides for each. This decomposition significantly aids in the construction of suitable variational families, enabling, in turn, substantial improvements in inference performance.
Probabilistic ProgrammingVariational InferenceStochastic Support
BibTeX
@inproceedings{
reichelt2022rethinking,
title={Rethinking Variational Inference for Probabilistic Programs with Stochastic Support},
author={Tim Reichelt and Luke Ong and Tom Rainforth},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=wjClgX-muzB}
}