Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs
Abstract
We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH). This algorithm extends Lightweight Metropolis-Hastings (LMH) by adjusting the probabilities of proposing random variables for modification to improve convergence of the program output. We show that AdLMH converges to the correct equilibrium distribution and compare convergence of AdLMH to that of LMH on several test problems to highlight different aspects of the adaptation scheme. We observe consistent improvement in convergence on the test problems.
Cite
Text
Tolpin et al. "Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2015. doi:10.1007/978-3-319-23525-7_19Markdown
[Tolpin et al. "Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2015.](https://mlanthology.org/ecmlpkdd/2015/tolpin2015ecmlpkdd-outputsensitive/) doi:10.1007/978-3-319-23525-7_19BibTeX
@inproceedings{tolpin2015ecmlpkdd-outputsensitive,
title = {{Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs}},
author = {Tolpin, David and van de Meent, Jan-Willem and Paige, Brooks and Wood, Frank D.},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2015},
pages = {311-326},
doi = {10.1007/978-3-319-23525-7_19},
url = {https://mlanthology.org/ecmlpkdd/2015/tolpin2015ecmlpkdd-outputsensitive/}
}