Fit the single factor MFAI model with partially observed main data matrix.

Usage

fitSFMissing(
  Y,
  X,
  init,
  obs_indices,
  learning_rate,
  tree_parameters,
  stage1 = TRUE,
  iter_max = 5000,
  tol_stage1 = 0.1,
  tol_stage2 = 1e-08,
  verbose_sf = TRUE,
  verbose_loop = TRUE,
  save_tree_list = TRUE
)

Arguments

Y: Main data matrix.
X: A data.frame containing the auxiliary information.
init: A MFAIRSingleFactor object containing the initial parameters for the single factor MAFI model.
obs_indices: Indices of the observed entries in the main data matrix.
learning_rate: Numeric. Parameter for the gradient boosting part.
tree_parameters: A list containing the parameters for the gradient boosting part.
stage1: Logical. Whether to perform fitting algorithm stage1. The greedy algorithm needs while the backfitting algorithm does not need.
iter_max: Integer. Maximum iterations allowed.
tol_stage1: Numeric. Convergence criterion in the first step.
tol_stage2: Numeric. Convergence criterion in the first step.
verbose_sf: Logical. Whether to display the detailed information.
verbose_loop: Logical. Whether to display the detailed information when looping.
save_tree_list: Logical. Whether to save the tree list.

Value

A MFAIRSingleFactor object containing the information about the fitted single factor MFAI model.