deephyper.search.nas¶
Neural architecture search algorithms.

class
deephyper.search.nas.
AMBSMixed
(problem, evaluator, random_state=None, log_dir='.', verbose=0, surrogate_model: str = 'RF', acq_func: str = 'UCB', kappa: float = 1.96, xi: float = 0.001, n_points: int = 10000, liar_strategy: str = 'cl_max', n_jobs: int = 1, **kwargs)[source]¶ Bases:
deephyper.search.nas._base.NeuralArchitectureSearch
Asynchronous ModelBased Search baised on the ScikitOptimized Optimizer. It is extended to the case of joint hyperparameter and neural architecture search.
 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.
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
1.96
for a balance between exploitation and exploration.xi (float, optional) – Manage the exploration/exploitation tradeoff of
"EI"
and"PI"
acquisition function. Defaults to0.001
for a balance between exploitation and exploration.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
.

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM

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 = 1e06, 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”.

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM

class
deephyper.search.nas.
NeuralArchitectureSearch
(problem, evaluator, random_state=None, log_dir='.', verbose=0, **kwargs)[source]¶ Bases:
deephyper.search._search.Search

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM


class
deephyper.search.nas.
Random
(problem, evaluator, random_state: Optional[int] = None, log_dir: str = '.', verbose: int = 0, **kwargs)[source]¶ Bases:
deephyper.search.nas._base.NeuralArchitectureSearch
Random neural architecture search. This search algorithm is compatible with a
NaProblem
defining fixed or variable hyperparameters. 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 or RandomState, 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.

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM

class
deephyper.search.nas.
RegularizedEvolution
(problem, evaluator, random_state: Optional[int] = None, log_dir: str = '.', verbose: int = 0, population_size: int = 100, sample_size: int = 10, **kwargs)[source]¶ Bases:
deephyper.search.nas._base.NeuralArchitectureSearch
Regularized evolution neural architecture search. This search is only compatible with a
NaProblem
that has fixed hyperparameters. 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.

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM

class
deephyper.search.nas.
RegularizedEvolutionMixed
(problem, evaluator, random_state: Optional[int] = None, log_dir: str = '.', verbose: int = 0, population_size: int = 100, sample_size: int = 10, **kwargs)[source]¶ Bases:
deephyper.search.nas._regevo.RegularizedEvolution
Extention of the Regularized evolution neural architecture search to the case of joint hyperparameter and neural architecture search.
 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.

search
(max_evals: int =  1, timeout: Optional[int] = None)¶ Execute the search algorithm.
 Parameters
 Returns
a pandas DataFrame containing the evaluations performed.
 Return type
DataFrame

terminate
()¶ Terminate the search.
 Raises
SearchTerminationError – raised when the search is terminated with SIGALARM