Distributed and Adaptive Darting Monte Carlo through Regenerations
Year: 2013
Type: conference-paper
Abstract: Darting Monte Carlo (DMC) is a MCMC proce-dure designed to effectively mix between multi-ple modes of a probability distribution. We pro-pose an adaptive and distributed version of this method by using regenerations. This allows us to run multiple chains in parallel and adapt the shape of the jump regions as well as all other as-pects of the Markov chain on the fly. We show that this significantly improves the performance of DMC because 1) a population of chains has a higher chance of finding the modes in the dis-tribution, 2) jumping between modes becomes easier due to the adaptation of their shapes, 3) computation is much more efficient due to paral-lelization across multiple processors. While the curse of dimensionality is a challenge for both DMC and regeneration, we find that their combi-nation ameliorates this issue slightly. 1
Authors: Sungjin Ahn, Yutian Chen, Max Welling
Institutions: University of California, Irvine, University of Amsterdam
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2102121202