Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling

Abstract

We propose a generalized Gibbs sampler algorithm for obtaining samples approximately distributed from a high-dimensional Gaussian distribution. Similarly to Hogwild methods, our approach does not target the original Gaussian distribution of interest, but an approximation to it. Contrary to Hogwild methods, a single parameter allows us to trade bias for variance. We show empirically that our method is very flexible and performs well compared to Hogwild-type algorithms.

Cite

Text

Barbos et al. "Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling." Neural Information Processing Systems, 2017.

Markdown

[Barbos et al. "Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/barbos2017neurips-clone/)

BibTeX

@inproceedings{barbos2017neurips-clone,
  title     = {{Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling}},
  author    = {Barbos, Andrei-Cristian and Caron, Francois and Giovannelli, Jean-François and Doucet, Arnaud},
  booktitle = {Neural Information Processing Systems},
  year      = {2017},
  pages     = {5020-5028},
  url       = {https://mlanthology.org/neurips/2017/barbos2017neurips-clone/}
}