Companion code to the preprint Baker, Fearnhead, Fox, Nemeth (2017) Control Variates for Stochastic Gradient MCMC. This code implements each of the Experiments. For the comparison section available in version 1, please see the repo BigDataMCMCComparisons.

If you want an easy way to implement SGMCMC algorithms (including control variate algorithms), consider using the R package sgmcmc which has a lot of easy to implement packages. Companion paper for the package available here.

For details of how to run the code, please see other READMEs.