Objects of class "grpl.control" define options such as bounds on the Hessian, convergence criteria and output management for the Group Lasso algorithm.
Objects can be created by calls of the form grpl.control(...)
save.xa logical indicating whether the design matrix should be saved.
save.ya logical indicating whether the response should be saved.
update.hessshould the hessian be updated in each iteration ("always")? update.hess = "lambda" will update the Hessian once for each component of the penalty parameter "lambda" based on the parameter estimates corresponding to the previous value of the penalty parameter.
update.everyOnly used if update.hess = "lambda". E.g. set to 3 if you want to update the Hessian only every third grid point.
inner.loopsHow many loops should be done (at maximum) when solving only the active set (without considering the remaining predictors). Useful if the number of predictors is large. Set to 0 if no inner loops should be performed.
line.searchShould line searches be performed?
max.iterMaximal number of loops through all groups
tolconvergence tolerance; the smaller the more precise.
lowerlower bound for the diagonal approximation of the corresponding block submatrix of the Hessian of the negative log-likelihood function.
upperupper bound for the diagonal approximation of the corresponding block submatrix of the Hessian of the negative log-likelihood function.
betascaling factor \(\beta < 1\) of the Armijo line search.
sigma\(0 < \sigma < 1\) used in the Armijo line search.
traceinteger. 1 prints the current lambda value,
2 prints the improvement in the objective function after each
sweep through all the parameter groups and additional information.
For the convergence criteria see chapter 8.2.3.2 of Gill et al. (1981).
Philip E. Gill, Walter Murray and Margaret H. Wright (1981) Practical Optimization, Academic Press.
Dimitri P. Bertsekas (2003) Nonlinear Programming, Athena Scientific.