Parallel Chromatic MCMC with Spatial Partitioning
This addresses a bottleneck in computational efficiency for spatial statistical models, though it appears incremental as it builds on existing MCMC and partitioning techniques.
The paper tackles the problem of parallelizing MCMC inference for models with spatial conditional independence, using a seismic event detection model as a case study, and achieves significant speedups over serial MCMC without quality degradation.
We introduce a novel approach for parallelizing MCMC inference in models with spatially determined conditional independence relationships, for which existing techniques exploiting graphical model structure are not applicable. Our approach is motivated by a model of seismic events and signals, where events detected in distant regions are approximately independent given those in intermediate regions. We perform parallel inference by coloring a factor graph defined over regions of latent space, rather than individual model variables. Evaluating on a model of seismic event detection, we achieve significant speedups over serial MCMC with no degradation in inference quality.