The occlusion process is a parallel, variational-assisted wrapper that decorrelates MCMC samples and provably inherits LLN, normed convergence, and geometric ergodicity, with empirical variance reduction when the variational proposal is good.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.CO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The occlusion process: improving sampler performance with parallel computation and variational approximation
The occlusion process is a parallel, variational-assisted wrapper that decorrelates MCMC samples and provably inherits LLN, normed convergence, and geometric ergodicity, with empirical variance reduction when the variational proposal is good.