Nested Sampling for Potts Models
Abstract
Nested sampling is a new Monte Carlo method by Skilling [1] intended for general Bayesian computation. Nested sampling provides a robust alternative to annealing-based methods for computing normalizing constants. It can also generate estimates of other quantities such as posterior expectations. The key technical requirement is an ability to draw samples uniformly from the prior sub ject to a constraint on the likelihood. We provide a demonstration with the Potts model, an undirected graphical model.
Cite
Text
Murray et al. "Nested Sampling for Potts Models." Neural Information Processing Systems, 2005.Markdown
[Murray et al. "Nested Sampling for Potts Models." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/murray2005neurips-nested/)BibTeX
@inproceedings{murray2005neurips-nested,
title = {{Nested Sampling for Potts Models}},
author = {Murray, Iain and MacKay, David and Ghahramani, Zoubin and Skilling, John},
booktitle = {Neural Information Processing Systems},
year = {2005},
pages = {947-954},
url = {https://mlanthology.org/neurips/2005/murray2005neurips-nested/}
}