Accelerating MCMC via Parallel Predictive Prefetching

Thirtieth Conference on Uncertainty in Artificial Intelligence (UAI) (2014)
arXiv:1403.7265 [stat.ML] | PDF | Google Doc | Code | Google Scholar | BibTex | EndNote


Parallel predictive prefetching is a new frame- work for accelerating a large class of widely-used Markov chain Monte Carlo (MCMC) algorithms. It speculatively evaluates many potential steps of an MCMC chain in parallel while exploiting fast, iterative approximations to the tar- get density. This can accelerate sampling from target distributions in Bayesian inference problems. Our approach takes advantage of whatever parallel resources are available, but produces results exactly equivalent to standard serial execution. In the initial burn-in phase of chain evaluation, we achieve speedup close to linear in the number of available cores.


markov chain monte carlo