Random Search

class hpbandster.optimizers.randomsearch.RandomSearch(configspace=None, eta=3, min_budget=1, max_budget=1, **kwargs)[source]

Implements a random search across the search space for comparison. Candidates are sampled at random and run on the maximum budget.

  • configspace (ConfigSpace object) – valid representation of the search space
  • eta (float) – In each iteration, a complete run of sequential halving is executed. In it, after evaluating each configuration on the same subset size, only a fraction of 1/eta of them ‘advances’ to the next round. Must be greater or equal to 2.
  • budget (float) – budget for the evaluation
get_next_iteration(iteration, iteration_kwargs={})[source]

Returns a SH iteration with only evaluations on the biggest budget

Parameters:iteration (int) – the index of the iteration to be instantiated
Returns:SuccessiveHalving – corresponding number of configurations
Return type:the SuccessiveHalving iteration with the