Combining mirror-reflection proposals with a Langevin gradient drift yields an MCMC method that the authors show to be faster per unit time than HMC/NUTS on Bayesian GLMMs.
Springer Texts in Statistics, 274 (2004)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.CO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Efficient Mirror-type Kernels for the Metropolis-Hastings Algorithm
Combining mirror-reflection proposals with a Langevin gradient drift yields an MCMC method that the authors show to be faster per unit time than HMC/NUTS on Bayesian GLMMs.