lda_fgs_hs: The LDA Full Gibbs sampler (FGS) with Selection of h

In clintpgeorge/ldamcmc: Markov chain Monte Carlo Algorithms for the Latent Dirichlet Allocation Model

Description

This a Markov chain on (z, β, θ)

Usage

lda_fgs_hs(K, V, wid, doc.N, alpha, eta, h.grid, max.iter, burn.in, spacing,
  save.z, save.beta, save.theta, save.Bh, save.lp)

Arguments

K	the number of topics in the corpus
V	the vocabulary size
wid	the vocabulary ids of every word instance in each corpus document
doc.N	the document lengths
alpha	the hyper parameter for θ
eta	the β matrix smoothing parameter
h.grid	the grid of hyperparamets (η, α), 2 x G matrix, where G is the number of grid points and the first row is for α points and the second row is for η points
max.iter	the max number of Gibbs iterations to be performed
burn.in	the burn in period of the Gibbs sampler
spacing	the spacing between the stored samples (to reduce correlation)
save.z	if 0 the function does not save z samples
save.beta	if 0 the function does not save β samples
save.theta	if 0 the function does not save θ samples
save.Bh	if 0 the function does not save computed B(h, h_*) values for iterations
save.lp	if 0 the function does not save computed log posterior for iterations

Value

the Gibbs sampling output

See Also

Other Gibbs sampling methods: get_grid_neighbors, lda_acgs_hs, lda_acgs, lda_fgs_st, lda_fgs

clintpgeorge/ldamcmc documentation built on Feb. 22, 2020, 12:39 p.m.