Calibrate topic proportions based on sufficient statistics

Calibrate topic proportions based on sufficient statistics

Usage

asap_topic_pmf_rbind(
  beta_dk_list,
  R_nk_list,
  Y_n_list,
  a0 = 1,
  b0 = 1,
  max_iter = 10L,
  NUM_THREADS = 1L,
  stdize_r = TRUE,
  verbose = TRUE
)

Arguments

beta_dk_list

a list of dictionary matrices (feature D x factor K)

R_nk_list

a list of correlation matrices (sample N x factor K)

Y_n_list

a list of sum vectors (sample N x 1)

a0

gamma(a0, b0) (default: 1)

b0

gamma(a0, b0) (default: 1)

max_iter

maximum iterations (default: 10)

NUM_THREADS

number of parallel threads (default: 1)

stdize_r

standardize correlation matrix R (default: TRUE)

verbose

(default: TRUE)

Value

a list that contains:

• theta (N x K) matrix

• log.theta (N x K) log matrix

• log.theta.sd (N x K) standard deviation matrix