A function to solve low rank plus sparse model estimation
fista.LpS(
A,
b,
lambda,
mu,
alpha_L = 0.25,
niter = 100,
backtracking = TRUE,
x.true
)A list object, including the followings
Estimated sparse component
Estimated low-rank component
Values of objective function
Relative errors compared with the true model parameters if available
A design matrix with size of n by p
A matrix, (or vector) with size of n by p (or n by 1)
A positive numeric value, indicating the tuning parameter for sparse component
A positive numeric value, indicating the tuning parameter for low rank component
The constraint coefficient of low rank component, default is 0.25
The maximum number of iterations required for FISTA
A boolean argument, indicating that use backtracking in the FISTA
A p by p matrix, the true model parameter. Only available for simulation.