ML Anthology

Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends

Christopher Tosh
ICML 2016 pp. 840-849
/icml/2016/tosh2016icml-mixing/

Abstract

Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants.

PDF ICML Semantic Scholar

Cite

Text

Tosh. "Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends." International Conference on Machine Learning, 2016.

Markdown

[Tosh. "Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/tosh2016icml-mixing/)

BibTeX

@inproceedings{tosh2016icml-mixing,
  title     = {{Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends}},
  author    = {Tosh, Christopher},
  booktitle = {International Conference on Machine Learning},
  year      = {2016},
  pages     = {840-849},
  volume    = {48},
  url       = {https://mlanthology.org/icml/2016/tosh2016icml-mixing/}
}