SLOPE()as a convergence criterion for the FISTA solver that sets a tolerance for the relative change in coefficients across iterations.
sigma) is now invariant to the number of observations, which is achieved by scaling the penalty part of the objective by the square root of the number of observations if
scale = "l2"and the number of observations if
scale = "sd"or
"none". No scaling is applied when
scale = "l1".
sigmaargument is deprecated in favor of
n_sigmaargument is deprecated in favor of
lambda_min_ratioargument is deprecated in favor of
SLOPE()has changed from
scale = "sd"now scales with the population standard deviation rather than the sample standard deviation, i.e. the scaling factor now used is the number of observations (and not the number of observations minus one as before).
path_lengthhas changed from 100 to 20.
plot.SLOPE()has gained an argument
x_variablethat controls what is plotted on the x axis.
max_variablescriterion is hit, the solution path returned will now include also the last solution (which was not the case before). Thanks, @straw-boy.
This version of SLOPE represents a major change to the package. We have merged functionality from the owl package into this package, which means there are several changes to the API, including deprecated functions.
create_lambda()have been deprecated (and will be defunct in the next version of SLOPE)
normalizehave been deprecated in
SLOPE()and replaced by
SLOPE()have been deprecated and replaced with
"admm", which uses the accelerated proximal gradient method FISTA and alternating direction of multipliers method (ADMM) respectively
family = "gaussian"
lambdais now scaled (divided by) the number of observations (rows) in
screen = TRUEin
SLOPE(). The type of algorithm can also be set via
SLOPE()now returns an object of class
"SLOPE"(and an additional class depending on input to
SLOPEnow uses screening rules to speed up model fitting in the high-dimensional regime
trainSLOPE()trains SLOPE with repeated k-folds cross-validation
caretSLOPE()enables model-tuning using the caret package
SLOPE()now fits an entire path of regularization sequences by default
SLOPE()has been replaced by
center, which allows granular options for standardization
deviance()returns the deviance from the fit
score()can be used to assess model performance against new data
plotDiagnostics()has been included to visualize data from the solver (if
diagnostics = TRUEin the call to
lambda = "oscar" in the call toSLOPE()`