(Experimental) Optimize a ULasso linear regression model by coordinate descent algorithm using a covariance matrix with R
cov_cda_r2(Gamma, gamma, lambda, R, init.beta, delta, maxit, eps, warm, strong,
sparse)
covariance matrix of explanatory variables
covariance vector of explanatory and objective variables
lambda sequence
matrix using exclusive penalty term
initial values of beta
ratio of regularization between l1 and exclusive penalty terms
max iteration
convergence threshold for optimization
warm start direction: "lambda" (default) or "delta"
whether use strong screening or not
whether use sparse matrix or not
standardized beta