For a given lambda, construct the sets of relevant variables for each cluster.
selectVariables(
phiInit,
rhoInit,
piInit,
gamInit,
mini,
maxi,
gamma,
glambda,
X,
Y,
thresh = 1e-08,
eps,
ncores = 3,
fast
)an initial estimator for phi (size: p*m*k)
an initial estimator for rho (size: m*m*k)
an initial estimator for pi (size : k)
an initial estimator for gamma
minimum number of iterations in EM algorithm
maximum number of iterations in EM algorithm
power in the penalty
grid of regularization parameters
matrix of regressors
matrix of responses
real, threshold to say a variable is relevant, by default = 1e-8
threshold to say that EM algorithm has converged
Number or cores for parallel execution (1 to disable)
boolean to enable or not the C function call
a list, varying lambda in a grid, with selected (the indices of variables that are selected), Rho (the covariance parameter, reparametrized), Pi (the proportion parameter)