ICML 2017poster39 citations
Stochastic Bouncy Particle Sampler
Ari Pakman, Dar Gilboa, David Carlson, Liam Paninski
Abstract
We introduce a stochastic version of the non-reversible, rejection-free Bouncy Particle Sampler (BPS), a Markov process whose sample trajectories are piecewise linear, to efficiently sample Bayesian posteriors in big datasets. We prove that in the BPS no bias is introduced by noisy evaluations of the log-likelihood gradient. On the other hand, we argue that efficiency considerations favor a small, controllable bias, in exchange for faster mixing. We introduce a simple method that controls this trade-off. We illustrate these ideas in several examples which outperform previous approaches.
BibTeX
@InProceedings{pmlr-v70-pakman17a,
title = {Stochastic Bouncy Particle Sampler},
author = {Ari Pakman and Dar Gilboa and David Carlson and Liam Paninski},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {2741--2750},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/pakman17a/pakman17a.pdf},
url = {https://proceedings.mlr.press/v70/pakman17a.html},
abstract = {We introduce a stochastic version of the non-reversible, rejection-free Bouncy Particle Sampler (BPS), a Markov process whose sample trajectories are piecewise linear, to efficiently sample Bayesian posteriors in big datasets. We prove that in the BPS no bias is introduced by noisy evaluations of the log-likelihood gradient. On the other hand, we argue that efficiency considerations favor a small, controllable bias, in exchange for faster mixing. We introduce a simple method that controls this trade-off. We illustrate these ideas in several examples which outperform previous approaches.}
}