deephyper.search.nas.AgEBO
deephyper.search.nas.AgEBO#
-
class
deephyper.search.nas.
AgEBO
(problem, evaluator, random_state: Optional[int] = None, log_dir: str = '.', verbose: int = 0, population_size: int = 100, sample_size: int = 10, surrogate_model: str = 'RF', acq_func: str = 'UCB', kappa: float = 0.001, xi: float = 1e-06, n_points: int = 10000, liar_strategy: str = 'cl_max', n_jobs: int = 1, mode: str = 'async', **kwargs)[source]# Bases:
deephyper.search.nas._regevo.RegularizedEvolution
Aging evolution with Bayesian Optimization.
This algorithm build on the Regularized Evolution. It cumulates Hyperparameter optimization with Bayesian optimisation and Neural architecture search with regularized evolution.
- Parameters
problem (NaProblem) – Neural architecture search problem describing the search space to explore.
evaluator (Evaluator) – An
Evaluator
instance responsible of distributing the tasks.random_state (int, optional) – Random seed. Defaults to None.
log_dir (str, optional) – Log directory where search’s results are saved. Defaults to “.”.
verbose (int, optional) – Indicate the verbosity level of the search. Defaults to 0.
population_size (int, optional) – the number of individuals to keep in the population. Defaults to
100
.sample_size (int, optional) – the number of individuals that should participate in each tournament. Defaults to
10
.surrogate_model (str, optional) – Surrogate model used by the Bayesian optimization. Can be a value in
["RF", "ET", "GBRT", "DUMMY"]
. Defaults to"RF"
.acq_func (str, optional) – Acquisition function used by the Bayesian optimization. Can be a value in
["UCB", "EI", "PI", "gp_hedge"]
. Defaults to"UCB"
.kappa (float, optional) – Manage the exploration/exploitation tradeoff for the “UCB” acquisition function. Defaults to
0.001
for strong exploitation.xi (float, optional) – Manage the exploration/exploitation tradeoff of
"EI"
and"PI"
acquisition function. Defaults to0.000001
for strong exploitation.n_points (int, optional) – The number of configurations sampled from the search space to infer each batch of new evaluated configurations. Defaults to
10000
.liar_strategy (str, optional) – Definition of the constant value use for the Liar strategy. Can be a value in
["cl_min", "cl_mean", "cl_max"]
. Defaults to"cl_max"
.n_jobs (int, optional) – Number of parallel processes used to fit the surrogate model of the Bayesian optimization. A value of
-1
will use all available cores. Defaults to1
.mode (str, optional) – Define if the search should be asynchronous or batch synchronous. Choice in [“sync”, “async”]. Defaults to “async”.
Methods
Dumps the context in the log folder.
Execute the search algorithm.
Terminate the search.
Returns a json version of the search object.
-
dump_context
()# Dumps the context in the log folder.
-
search
(max_evals: int = - 1, timeout: Optional[int] = None)# Execute the search algorithm.
- Parameters
- Returns
a pandas DataFrame containing the evaluations performed or
None
if the search could not evaluate any configuration.- Return type
DataFrame
-
terminate
()# Terminate the search.
- Raises
SearchTerminationError – raised when the search is terminated with SIGALARM
-
to_json
()# Returns a json version of the search object.