syne_tune.optimizer.schedulers.searchers.regularized_evolution module

class syne_tune.optimizer.schedulers.searchers.regularized_evolution.PopulationElement(score=0, config=None, results=None)

Bases: object

score: float = 0

config: Dict[str, Any] = None

results: List[float] = None

syne_tune.optimizer.schedulers.searchers.regularized_evolution.mutate_config(config, config_space, rng, num_try=1000)

Return type:

Dict[str, Any]

syne_tune.optimizer.schedulers.searchers.regularized_evolution.sample_random_config(config_space, rng)

Return type:

Dict[str, Any]

class syne_tune.optimizer.schedulers.searchers.regularized_evolution.RegularizedEvolution(config_space, points_to_evaluate=None, population_size=100, sample_size=10, random_seed=None)

Bases: SingleObjectiveBaseSearcher

Implements the regularized evolution algorithm. The original implementation only considers categorical hyperparameters. For integer and float parameters we sample a new value uniformly at random. Reference:

Real, E., Aggarwal, A., Huang, Y., and Le, Q. V.

Regularized Evolution for Image Classifier Architecture Search.

In Proceedings of the Conference on Artificial Intelligence (AAAI’19)

The code is based one the original regularized evolution open-source implementation: https://colab.research.google.com/github/google-research/google-research/blob/master/evolution/regularized_evolution_algorithm/regularized_evolution.ipynb

Additional arguments on top of parent class StochasticSearcher:

Parameters:

• population_size (int) – Size of the population, defaults to 100

• sample_size (int) – Size of the candidate set to obtain a parent for the mutation, defaults to 10

suggest(**kwargs)

Suggest a new configuration.

Note: Query _next_points_to_evaluate() for initial configs to return first.

Parameters:

kwargs – Extra information may be passed from scheduler to searcher

Return type:

Optional[dict]

Returns:

New configuration. The searcher may return None if a new configuration cannot be suggested. In this case, the tuning will stop. This happens if searchers never suggest the same config more than once, and all configs in the (finite) search space are exhausted.

on_trial_complete(trial_id, config, metric)

Inform searcher about result

The scheduler passes every result. If update == True, the searcher should update its surrogate model (if any), otherwise result is an intermediate result not modelled.

The default implementation calls _update() if update == True. It can be overwritten by searchers which also react to intermediate results.

Parameters:

• trial_id (int) – See on_trial_result()

• config (Dict[str, Any]) – See on_trial_result()

• metric (float) – See on_trial_result()