paraqeet.optimizers.bayesian_optimizer.BayesianOptimizer#

class paraqeet.optimizers.bayesian_optimizer.BayesianOptimizer(measure, optimization_map, initial_samples=10, iterations=100)#

Bases: Optimizer

Minimizes the outcome of a measuremnt using Bayesian optimization.

This is useful if the evaluation of the measurement is costly. This class is mostly a wrapper around the implementing package.

See also

https: //bayesian-optimization.github.io/BayesianOptimization/index.html

Parameters:

measure (Measurement) – The measure to be optimized.
optimization_map (OptimizationMap) – All optimizable parameters via the optimization map.
initial_samples (int=10) – Number of iterations before the explorations starts the exploration for the maximum.
iterations (int =100) – Number of iterations where the method attempts to find the maximum value.

__init__(measure, optimization_map, initial_samples=10, iterations=100)#

Parameters:

measure (NormalizableMeasurement)
optimization_map (OptimizationMap)

Methods

`__init__`(measure, optimization_map[, ...])
`optimize`(times)	Optimize the system via the Bayesian optimizer.

Attributes

`initial_samples`	Get the initial samples fed to the system.
`iterations`	Get the iterations of the system.
`logger`	Returns the current logger that is being used by this optimizer, or None if no logger was set yet.
`optimization_map`	Return the optimization map that this optimizer uses.

property initial_samples: int#: Get the initial samples fed to the system.

property iterations: int#: Get the iterations of the system.

property logger: Logger | None#: Returns the current logger that is being used by this optimizer, or None if no logger was set yet.

property optimization_map: OptimizationMap#

Return the optimization map that this optimizer uses.

Parameters that can be optimized need to be added to this map.

Returns:: Returns the optimization map that this optimizer uses.
Return type:: paraqeet.optimization_map

optimize(times)#

Optimize the system via the Bayesian optimizer.

Performs the actual optimization.

Note - If input `times` is a float, then the start time of propagation is implicitly assumed to be zero. For an array of times, the first time point is the start time.

Returns:: Result of optimization via the OptimizationResult object. (status, value, iterations and the raw result)
Return type:: OptimizationResult
Parameters:: times (Array | float)