CADETProcess.optimization.COBYLA

class CADETProcess.optimization.COBYLA(rhobeg, tol, maxiter, disp, catol, f_tol, cv_tol, n_max_evals, n_max_iter, finite_diff_rel_step, jac, progress_frequency, x_tol, similarity_tol, parallelization_backend)

Wrapper for the COBYLA optimization method from the scipy optimization suite.

It defines the solver options in the ‘options’ variable as a dictionary.

Supports:

• Linear constraints

• Linear equality constraints

• Nonlinear constraints

Parameters:

rhobegfloat, default 1

Reasonable initial changes to the variables.

tolfloat, default 0.0002

Final accuracy in the optimization (not precisely guaranteed). This is a lower bound on the size of the trust region.

dispbool, default False

Set to True to print convergence messages. If False, verbosity is ignored and set to 0.

maxiterint, default 10000

Maximum number of function evaluations.

catolfloat, default 2e-4

Absolute tolerance for constraint violations.

Attributes:

aggregated_parameters

dict: Aggregated parameters of the instance.

catol

cv_tol

disp

f_tol

finite_diff_rel_step

jac

maxiter

missing_parameters

list: Parameters that are required but not set.

n_cores

int: Proxy to the number of cores used by the parallelization backend.

n_max_evals

n_max_iter

options

dict: Optimizer options.

parallelization_backend

parameters

dict: Parameters of the instance.

polynomial_parameters

dict: Polynomial parameters of the instance.

progress_frequency

required_parameters

list: Parameters that have no default value.

rhobeg

similarity_tol

sized_parameters

dict: Sized parameters of the instance.

specific_options

dict: Optimizer spcific options.

tol

x_tol

Methods

check_optimization_problem(optimization_problem)	Check if problem is configured correctly and supported by the optimizer.
check_required_parameters()	Verify if all required parameters are set.
check_x0(optimization_problem, x0)	Check the initial guess x0 for an optimization problem.
get_bounds(optimization_problem)	Returns the optimized bounds of a given optimization_problem as a Bound object.
get_constraint_objects(optimization_problem)	Return constraints as objets.
get_lincon_obj(optimization_problem)	Return the linear constraints as an object.
get_lineqcon_obj(optimization_problem)	Return the linear equality constraints as an object.
get_nonlincon_obj(optimization_problem)	Return the optimized nonlinear constraints as an object.
optimize(optimization_problem[, x0, ...])	Solve OptimizationProblem.
run(optimization_problem[, x0])	Solve the optimization problem using any of the scipy methods.
run_post_processing(X_transformed, ...[, ...])	Run post-processing of generation.

run_final_processing