ML Anthology

Fast Markov Chain Monte Carlo Algorithms via Lie Groups

Steve Huntsman
AISTATS 2020 pp. 2841-2851
/aistats/2020/huntsman2020aistats-fast/

Abstract

From basic considerations of the Lie group that preserves a target probability measure, we derive the Barker, Metropolis, and ensemble Markov chain Monte Carlo (MCMC) algorithms, as well as variants of waste-recycling Metropolis-Hastings and an altogether new MCMC algorithm. We illustrate these constructions with explicit numerical computations, and we empirically demonstrate on a spin glass that the new algorithm converges more quickly than its siblings.

PDF AISTATS Semantic Scholar

Cite

Text

Huntsman. "Fast Markov Chain Monte Carlo Algorithms via Lie Groups." Artificial Intelligence and Statistics, 2020.

Markdown

[Huntsman. "Fast Markov Chain Monte Carlo Algorithms via Lie Groups." Artificial Intelligence and Statistics, 2020.](https://mlanthology.org/aistats/2020/huntsman2020aistats-fast/)

BibTeX

@inproceedings{huntsman2020aistats-fast,
  title     = {{Fast Markov Chain Monte Carlo Algorithms via Lie Groups}},
  author    = {Huntsman, Steve},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2020},
  pages     = {2841-2851},
  volume    = {108},
  url       = {https://mlanthology.org/aistats/2020/huntsman2020aistats-fast/}
}