Optimized Weighted Average of Features for Classification and Regression
Computes a weighted average of inputs. Used in the context of computing weighted averages of predictions.
Predictions are averaged using
weights (in order of appearance in the data) which are optimized using
nonlinear optimization from the package "nloptr" for a measure provided in
measure (defaults to
Learned weights can be obtained from
Using non-linear optimization is implemented in the SuperLearner R package.
For a more detailed analysis the reader is referred to
LeDell, 2015: Scalable Ensemble Learning and Computationally Efficient Variance Estimation.
MeasureMeasure to optimized weights for. The Measure is either obtained from
mlr_measuresor directly supplied. Defaults to
character(1)Several nonlinear optimization methods from
nloptrare available. See
nloptr::nloptr.print.options()for a list of possible options. Note that we only allow for derivative free local or global algorithms, i.e. NLOPT_(G|L)N_.
LearnerClassifAvg$new(), id = "classif.avg")(
LearnerRegrAvg$new(), id = "regr.avg")(