Optimization via Random Search

OptimizerRandomSearch class that implements a simple Random Search.

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.

Source

Bergstra J, Bengio Y (2012). “Random Search for Hyper-Parameter Optimization.” Journal of Machine Learning Research, 13(10), 281--305. https://jmlr.csail.mit.edu/papers/v13/bergstra12a.html.

Dictionary

This Optimizer can be instantiated via the dictionary mlr_optimizers or with the associated sugar function opt():

mlr_optimizers$get("random_search")
opt("random_search")

Parameters

batch_size

integer(1)
Maximum number of points to try in a batch.

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").

Super class

bbotk::Optimizer -> OptimizerRandomSearch

Methods

Public methods

• OptimizerRandomSearch$new()

• OptimizerRandomSearch$clone()

Inherited methods

• bbotk::Optimizer$format()
• bbotk::Optimizer$help()
• bbotk::Optimizer$optimize()
• bbotk::Optimizer$print()

---

Method new()

Creates a new instance of this R6 class.

Usage

OptimizerRandomSearch$new()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

OptimizerRandomSearch$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

search_space = domain = ps(x = p_dbl(lower = -1, upper = 1))

codomain = ps(y = p_dbl(tags = "minimize"))

objective_function = function(xs) {
  list(y = as.numeric(xs)^2)
}

objective = ObjectiveRFun$new(
 fun = objective_function,
 domain = domain,
 codomain = codomain)

instance = OptimInstanceSingleCrit$new(
 objective = objective,
 search_space = search_space,
 terminator = trm("evals", n_evals = 10))


optimizer = opt("random_search")

# modifies the instance by reference
optimizer$optimize(instance)
#>             x  x_domain           y
#> 1: 0.05135715 <list[1]> 0.002637557

# returns best scoring evaluation
instance$result
#>             x  x_domain           y
#> 1: 0.05135715 <list[1]> 0.002637557

# allows access of data.table of full path of all evaluations
as.data.table(instance$archive$data)
#>               x           y  x_domain           timestamp batch_nr
#>  1:  0.32311590 0.104403882 <list[1]> 2023-11-13 12:08:07        1
#>  2: -0.89204026 0.795735820 <list[1]> 2023-11-13 12:08:07        2
#>  3: -0.10669202 0.011383186 <list[1]> 2023-11-13 12:08:07        3
#>  4: -0.74033703 0.548098915 <list[1]> 2023-11-13 12:08:07        4
#>  5: -0.22526185 0.050742899 <list[1]> 2023-11-13 12:08:07        5
#>  6: -0.24371196 0.059395519 <list[1]> 2023-11-13 12:08:07        6
#>  7: -0.45547755 0.207459798 <list[1]> 2023-11-13 12:08:07        7
#>  8: -0.22226503 0.049401746 <list[1]> 2023-11-13 12:08:07        8
#>  9:  0.05135715 0.002637557 <list[1]> 2023-11-13 12:08:07        9
#> 10: -0.07573335 0.005735540 <list[1]> 2023-11-13 12:08:07       10