estimate_lasso_parameters: Estimate Lasso regression parameters

In gersteinlab/siglasso: Optimizing Cancer Mutation Signatures Jointly with Sampling Likelihood

Estimate Lasso regression parameters

Description

Determine the lambda in lasso procedure emperically

Usage

estimate_lasso_parameters(
  predictor,
  p_star_hat,
  gamma,
  penalty,
  prior,
  adaptive,
  sd_multiplier,
  elastic_net = F
)

Arguments

predictor	A signature matrix
p_star_hat	The regression target
gamma	Hyperparameter for adaptive LASSO
penalty	A vector of relative penalties on signatures
prior	A vector of relative penalties on signatures given as prior
adaptive	Boolean variable, perform adaptive LASSO or not
sd_multiplier	How many SD should be tolerated from min MSE
elastic_net	Use Elastic_net instead of LASSO?

Value

Returns a list of updated parameters including lambda picked, predictors used, a sequence of lambdas searched, alpha (elastic net) picked and the OLS fitting results (for adpative LASSO)

gersteinlab/siglasso documentation built on Sept. 5, 2022, 8:45 p.m.