smt_optim package

Subpackages

• smt_optim.acquisition_strategies package
  • AcquisitionStrategy
  • MFSEGO
  • Submodules
  • smt_optim.acquisition_strategies.base module
  • smt_optim.acquisition_strategies.mfsego module
• smt_optim.benchmarks package
  • Submodules
  • smt_optim.benchmarks.avt module
  • smt_optim.benchmarks.base module
  • smt_optim.benchmarks.edge_cases module
  • smt_optim.benchmarks.gano module
  • smt_optim.benchmarks.modified_avt module
  • smt_optim.benchmarks.original module
  • smt_optim.benchmarks.registry module
• smt_optim.core package
  • ConstraintConfig
  • Driver
  • DriverConfig
  • Evaluator
  • ObjectiveConfig
  • OptimizationDataset
  • Problem
  • Sample
  • State
  • Submodules
  • smt_optim.core.driver module
  • smt_optim.core.problem module
  • smt_optim.core.sample module
  • smt_optim.core.state module
• smt_optim.subsolvers package
  • multistart_minimize()
  • Submodules
  • smt_optim.subsolvers.multistart module
• smt_optim.surrogate_models package
  • SmtAutoModel
  • SmtMFCK
  • Surrogate
  • Submodules
  • smt_optim.surrogate_models.base module
  • smt_optim.surrogate_models.smt module
• smt_optim.utils package
  • Submodules
  • smt_optim.utils.constraints module
  • smt_optim.utils.get_fmin module
  • smt_optim.utils.initial_design module
  • smt_optim.utils.json module
  • smt_optim.utils.logger module
  • smt_optim.utils.stop_criteria module

Submodules

smt_optim.acquisition_functions module

smt_optim.acquisition_functions.expected_improvement(mu: float, s2: float, f_min: float) → float

Expected Improvement acquisition function.

Parameters:

• mu (float) – Mean prediction.

• s2 (float) – Variance prediction.

• f_min (float) – Best minimum objective value in training data.

Returns:

Expected Improvement value.

Return type:

float

smt_optim.acquisition_functions.log_ei(mu: ndarray, s2: ndarray, f_min: float) → ndarray

Vectorized Log Expected Improvement acquisition function.

LogEI is more numerically stable that the EI acquisition function especially when the GP’s variance is small. From: https://arxiv.org/abs/2310.20708.

Parameters:

• mu (np.ndarray) – Mean prediction of shape (num_points, 1).

• s2 (np.ndarray) – Variance prediction of shape (num_points, 1).

• f_min (float) – Best minimum objective value in training data.

Return type:

np.ndarray

smt_optim.acquisition_functions.probability_of_improvement(mu: ndarray, s2: ndarray, f_min: float) → ndarray

Probability of Improvement acquisition function. :param mu: Mean prediction. :type mu: np.ndarray

Parameters:

• s2 (np.ndarray) – Variance prediction.

• f_min (np.ndarray) – Minimum predicted objective value.

Returns:

The PI acquisition function value.

Return type:

np.ndarray

smt_optim.acquisition_functions.vec_expected_improvement(mu: ndarray, s2: ndarray, f_min: float) → ndarray

Vectorized Expected Improvement acquisition function.

Parameters:

• mu (np.ndarray) – Mean prediction of shape (num_points, 1).

• s2 (np.ndarray) – Variance prediction of shape (num_points, 1).

• f_min (float) – Best minimum objective value in training data.

Returns:

Expected Improvement values of shape (num_points, 1).

Return type:

np.ndarray

smt_optim.frameworks module