Subclass for tuning w.r.t. fixed design points.
We simply search over a set of points fully specified by the user. The points in the design are evaluated in order as given.
Dictionary
This Tuner can be instantiated with the associated sugar function tnr()
:
tnr("design_points")
Parallelization
In order to support general termination criteria and parallelization, we
evaluate points in a batch-fashion of size batch_size
. Larger batches mean
we can parallelize more, smaller batches imply a more fine-grained checking
of termination criteria. A batch contains of batch_size
times resampling$iters
jobs.
E.g., if you set a batch size of 10 points and do a 5-fold cross validation, you can
utilize up to 50 cores.
Parallelization is supported via package future (see mlr3::benchmark()
's
section on parallelization for more details).
Logging
All Tuners use a logger (as implemented in lgr) from package
bbotk.
Use lgr::get_logger("bbotk")
to access and control the logger.
Optimizer
This Tuner is based on bbotk::OptimizerDesignPoints which can be applied on any black box optimization problem. See also the documentation of bbotk.
Parameters
batch_size
integer(1)
Maximum number of configurations to try in a batch.design
data.table::data.table
Design points to try in search, one per row.
Resources
There are several sections about hyperparameter optimization in the mlr3book.
Learn more about tuners.
The gallery features a collection of case studies and demos about optimization.
Use the Hyperband optimizer with different budget parameters.
Progress Bars
$optimize()
supports progress bars via the package progressr
combined with a Terminator. Simply wrap the function in
progressr::with_progress()
to enable them. We recommend to use package
progress as backend; enable with progressr::handlers("progress")
.
See also
Package mlr3hyperband for hyperband tuning.
Other Tuner:
mlr_tuners_cmaes
,
mlr_tuners_gensa
,
mlr_tuners_grid_search
,
mlr_tuners_irace
,
mlr_tuners_nloptr
,
mlr_tuners_random_search
,
mlr_tuners
Super classes
mlr3tuning::Tuner
-> mlr3tuning::TunerFromOptimizer
-> TunerDesignPoints
Examples
# Hyperparameter Optimization
# load learner and set search space
learner = lrn("classif.rpart",
cp = to_tune(1e-04, 1e-1),
minsplit = to_tune(2, 128),
minbucket = to_tune(1, 64)
)
# create design
design = mlr3misc::rowwise_table(
~cp, ~minsplit, ~minbucket,
0.1, 2, 64,
0.01, 64, 32,
0.001, 128, 1
)
# run hyperparameter tuning on the Palmer Penguins data set
instance = tune(
tuner = tnr("design_points", design = design),
task = tsk("penguins"),
learner = learner,
resampling = rsmp("holdout"),
measure = msr("classif.ce")
)
# best performing hyperparameter configuration
instance$result
#> cp minsplit minbucket learner_param_vals x_domain classif.ce
#> 1: 0.01 64 32 <list[4]> <list[3]> 0.06086957
# all evaluated hyperparameter configuration
as.data.table(instance$archive)
#> cp minsplit minbucket classif.ce x_domain_cp x_domain_minsplit
#> 1: 0.100 2 64 0.13913043 0.100 2
#> 2: 0.010 64 32 0.06086957 0.010 64
#> 3: 0.001 128 1 0.06086957 0.001 128
#> x_domain_minbucket runtime_learners timestamp batch_nr warnings
#> 1: 64 0.009 2023-03-09 07:19:01 1 0
#> 2: 32 0.008 2023-03-09 07:19:01 2 0
#> 3: 1 0.008 2023-03-09 07:19:01 3 0
#> errors resample_result
#> 1: 0 <ResampleResult[21]>
#> 2: 0 <ResampleResult[21]>
#> 3: 0 <ResampleResult[21]>
# fit final model on complete data set
learner$param_set$values = instance$result_learner_param_vals
learner$train(tsk("penguins"))