batch_size

Total batch size in parallel EGO

Specification

  • Alias: None

  • Arguments: INTEGER

  • JSON argument key: count

Child Keywords:

Required/Optional

Description of Group

JSON Group Key

Dakota Keyword

Dakota Keyword Description

Optional

synchronization

Select how Dakota schedules a batch of concurrent function evaluations in a parallel algorithm

Optional

exploration

Portion of batch size dedicated to exploration in parallel EGO

Description

Refinement candidates are generated by an acquisition function such as maximum expected improvement, which balances exploration and exploitation. Refinement candidates can also be generated by purely explorative metrics such as maximum prediction variance. For a specified batch_size, exploration specifies the subset of this total that will be dedicated to pure exploration of the parameter space.

Default Behavior All of the batch size is devoted to the standard acquisition approach, balancing exploration and exploitation.

Examples

method
  efficient_global
    seed = 1237
    batch_size = 8
    exploration = 2
{
  "method": [
    {
      "efficient_global": {
        "seed": 1237,
        "batch_size": {
          "count": 8,
          "exploration": 2
        }
      }
    }
  ]
}