Lambda_gird: Simulate a grid set of lambdas for a given alpha in penalized...

In xueweic/APGD: TGPred: Efficient methods for predicting target genes of a transcription factor by integrating statistics, machine learning, and optimization.

Simulate a grid set of lambdas for a given alpha in penalized regression.

Usage

Lambda_gird(X, y, n_lambda, alpha, loss_func)

Arguments

X	expression levels of n_genes target genes (TGs).
y	expression levels of a transcription factor (TF).
n_lambda	the number of lambdas.
alpha	the proportion of l1 norm affects (the numerical values of nonzero coefficients). Its in range (0,1].
loss_func	either "Huber" or "MSE". If loss_func = "Huber", the loss function in penalized regression model is Huber function. If loss_func = "MSE", the loss function in penalized regression model is mean squared errors.

Value

lambdas

n_lambda length vector of lambdas according to the alpha you provided.

Examples

alpha <- 0.5
    
n_lambda <- 10
    
lambda_set <- Lambda_grid(X, y, n_lambda, alpha, loss_func = "Huber")
    
lambda_set <- Lambda_grid(X, y, n_lambda, alpha, loss_func = "MSE")

xueweic/APGD documentation built on Sept. 4, 2023, 2:18 a.m.