Stochastic Bouncy Particle Sampler
[edit]
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:27412750, 2017.
Abstract
We introduce a stochastic version of the nonreversible, rejectionfree 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 loglikelihood 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 tradeoff. We illustrate these ideas in several examples which outperform previous approaches.
Related Material


