fusion_TA_mixG: Time-adapting Fusion
In rchan26/mixGaussTempering: What the Package Does (One Line, Title Case)

Description Usage Arguments Value Examples

Time-adapting Monte Carlo Fusion for sub-posteriors which are tempered mixture Gaussians with same weights, means, sds components

1 2	fusion_TA_mixG(N, time, C, samples_to_fuse, weights, means, sds, betas, sample_weights, level = 1, acceptance_rate = F, timed = F)

`N`	number of samples
`time`	time T for time-adapting fusion algorithm
`C`	number of sub-posteriors to combine
`samples_to_fuse`	list of length C, where samples_to_fuse[c] containg the samples for the c-th sub-posterior
`weights`	vector: weights of mixture Gaussian
`means`	vector: means of mixture Gassuan
`sds`	vector: st.devs of mixture Gaussian
`betas`	vector of length C, where betas[c] is the beta for c-th sub-posterior
`sample_weights`	defaults to betas if missing: vector of length C, where sample_weights[c] is the sample wieght for the c-th sub-posterior
`level`	defaults to 1, used in hierarchical and sequential Monte Carlo Fusion
`acceptance_rate`	boolean value: defaults to F, determines whether or not to return acceptance rates
`timed`	boolen value: defaults to T, determines whether or not to return the time elapsed to run
`betas`	vector of length C, where betas[c] is the beta for c-th sub-posterior

samples: fusion samples

iters_rho: number of iterations from the first accept/reject step (rho)

iters_Q: number of iterations from the second (diffusion) accept/reject step (Q)

time: run-time of fusion sampler

# setting variables
w_example <- c(0.35, 0.65)
m_example <- c(-3, 5)
s_example <- c(1, 1.5)
b_example <- 1/2

# sampling from tempered density
nsamples <- 500000
base <- hmc_base_sampler_mixG(w_example, m_example, s_example, b_example, nsamples, 2)

test <- fusion_TA_mixG(N = 10000, time = 1, C = 2, samples_to_fuse = base,
                       weights = w_example, means = m_example, sds = s_example,
                       betas = rep(b_example, 2), acceptance_rate = T, timed = T)