Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling

@InProceedings{pmlr-v48-sa16,
  title = 	 {Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling},
  author = 	 {Sa, Christopher De and Re, Chris and Olukotun, Kunle},
  booktitle = 	 {Proceedings of The 33rd International Conference on Machine Learning},
  pages = 	 {1567--1576},
  year = 	 {2016},
  editor = 	 {Balcan, Maria Florina and Weinberger, Kilian Q.},
  volume = 	 {48},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {New York, New York, USA},
  month = 	 {20--22 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v48/sa16.pdf},
  url = 	 {https://proceedings.mlr.press/v48/sa16.html},
  abstract = 	 {Gibbs sampling is a Markov chain Monte Carlo technique commonly used for estimating marginal distributions. To speed up Gibbs sampling, there has recently been interest in parallelizing it by executing asynchronously. While empirical results suggest that many models can be efficiently sampled asynchronously, traditional Markov chain analysis does not apply to the asynchronous case, and thus asynchronous Gibbs sampling is poorly understood. In this paper, we derive a better understanding of the two main challenges of asynchronous Gibbs: bias and mixing time. We show experimentally that our theoretical results match practical outcomes.}
}