https://github.com/cran/grplasso
Tip revision: 81dd97349c6c348d34778ab1a98ad221602285c4 authored by Lukas Meier on 11 February 2009, 00:00:00 UTC
version 0.3-2
version 0.3-2
Tip revision: 81dd973
grpl.control.Rd
\name{grpl.control}
\alias{grpl.control}
\title{Options for the Group Lasso Algorithm}
\description{
Definition of options such as bounds on the Hessian,
convergence criteria and output management for the Group Lasso algorithm.
}
\usage{
grpl.control(save.x = FALSE, save.y = TRUE,
update.hess = c("lambda", "always"), update.every = 3,
inner.loops = 10, line.search = TRUE, max.iter = 500,
tol = 5 * 10^-8, lower = 10^-2, upper = Inf, beta = 0.5,
sigma = 0.1, trace = 1)
}
\arguments{
\item{save.x}{a logical indicating whether the design matrix should be saved.}
\item{save.y}{a logical indicating whether the response should be saved.}
\item{update.hess}{should 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.}
\item{update.every}{Only used if update.hess = "lambda". E.g. set to 3
if you want to update the Hessian only every third grid point.}
\item{inner.loops}{How 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.}
\item{line.search}{Should line searches be performed?}
\item{max.iter}{Maximal number of loops through all groups}
\item{tol}{convergence tolerance; the smaller the more precise, see
details below.}
\item{lower}{lower bound for the diagonal approximation of the
corresponding block submatrix of the Hessian of the negative
log-likelihood function.}
\item{upper}{upper bound for the diagonal approximation of the
corresponding block submatrix of the Hessian of the negative
log-likelihood function.}
\item{beta}{scaling factor \eqn{\beta < 1} of the Armijo line search.}
\item{sigma}{\eqn{0 < \sigma < 1} used in the Armijo line search.}
\item{trace}{integer. \code{0} omits any output, \code{1} prints the
current lambda value, \code{2} prints the improvement in the
objective function after each sweep through all the parameter groups
and additional information.}
}
\details{For the convergence criteria see chapter 8.2.3.2 of Gill et
al. (1981).}
\references{Philip E. Gill, Walter Murray and Margaret H. Wright (1981)
\emph{Practical Optimization}, Academic Press.
Dimitri P. Bertsekas (2003) \emph{Nonlinear Programming}, Athena Scientific.}
\value{
An object of class \code{grpl.control}.
}
\keyword{misc}