Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices
Abstract
We present a new way of converting a reversible finite Markov chain into a nonreversible one, with a theoretical guarantee that the asymptotic variance of the MCMC estimator based on the non-reversible chain is reduced. The method is applicable to any reversible chain whose states are not connected through a tree, and can be interpreted graphically as inserting vortices into the state transition graph. Our result confirms that non-reversible chains are fundamentally better than reversible ones in terms of asymptotic performance, and suggests interesting directions for further improving MCMC.
Cite
Text
Sun et al. "Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices." Neural Information Processing Systems, 2010.Markdown
[Sun et al. "Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/sun2010neurips-improving/)BibTeX
@inproceedings{sun2010neurips-improving,
title = {{Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices}},
author = {Sun, Yi and Schmidhuber, Jürgen and Gomez, Faustino J.},
booktitle = {Neural Information Processing Systems},
year = {2010},
pages = {2235-2243},
url = {https://mlanthology.org/neurips/2010/sun2010neurips-improving/}
}