parallel_fusion_uniGaussian: Generalised Monte Carlo Fusion (rejection sampling)...

In rchan26/hierarchicalFusion: Divide-and-Conquer Monte Carlo Fusion

Generalised Monte Carlo Fusion (rejection sampling) [parallel]

Description

Generalised Monte Carlo Fusion with univariate Gaussian target

Usage

parallel_fusion_uniGaussian(
  N,
  m,
  time,
  samples_to_fuse,
  means,
  sds,
  betas,
  precondition_values,
  seed = NULL,
  n_cores = parallel::detectCores()
)

Arguments

N	number of samples
m	number of sub-posteriors to combine
time	time T for fusion algorithm
samples_to_fuse	list of length m, where samples_to_fuse[c] contains the samples for the c-th sub-posterior
means	vector of length m, where means[c] is the mean for c-th sub-posterior
sds	vector of length m, where sds[c] is the standard deviation for c-th sub-posterior
betas	vector of length m, where betas[c] is the inverse temperature (beta) for c-th sub-posterior (can also pass in one number if they are all at the same inverse temperature)
precondition_values	vector of length m, where precondition_values[c] is the precondition value for sub-posterior c
seed	seed number - default is NULL, meaning there is no seed
n_cores	number of cores to use

Value

A list with components:

samples

fusion samples

rho

acceptance rate for rho step

Q

acceptance rate for Q step

rhoQ

overall acceptance rate

time

run-time of fusion sampler

rho_iterations

number of iterations for rho step

Q_iterations

number of iterations for Q step

precondition_values

list of length 2 where precondition_values[[2]] are the pre-conditioning values that were used and precondition_values[[1]] are the combined precondition values

rchan26/hierarchicalFusion documentation built on Sept. 11, 2022, 10:30 p.m.