optimal_simlr_initializer.Rd
This function generates multiple random candidate U matrices, evaluates their associated energy (without gradient descent), and returns the best-scoring initialization. A seed parameter ensures reproducibility across runs.
optimal_simlr_initializer(
data_matrices,
n_init = 10,
basisK,
energyType = "acc",
domainMatrices = NULL,
domainLambdas = NULL,
verbose = TRUE,
seed = NULL
)
A list of modality-specific data matrices.
Number of random initializations to try (default = 10).
Number of basis components (columns in U).
Energy function to evaluate.
Optional list of domain priors (same length as data_matrices).
Optional vector of domain weights.
Logical, whether to print progress.
Optional numeric seed for reproducibility (default = NULL, no seed set).
A list with elements:
List of U matrices (one per modality) for the best initialization.
List of corresponding V matrices.
Mean energy for the selected initialization.