f3dasm.optimization package
Submodules
f3dasm.optimization.gpyopt_implementations module
- class f3dasm.optimization.gpyopt_implementations.BayesianOptimization(data: f3dasm.base.data.Data, hyperparameters: Optional[Mapping[str, Any]] = <factory>, seed: int = 81320, defaults: Optional[Mapping[str, Any]] = <factory>)
Bases:
f3dasm.base.optimization.OptimizerBayesian Optimization implementation from the GPyOPt library
- algorithm: Any
- data: f3dasm.base.data.Data
- defaults: Optional[Mapping[str, Any]]
- hyperparameters: Optional[Mapping[str, Any]]
- init_parameters()
Set the initialization parameters. This could be dynamic or static hyperparameters.
- set_algorithm()
If necessary, the algorithm needs to be set
- update_step(function: f3dasm.base.function.Function) None
One iteration of the algorithm. Adds the new input vector and resulting output immediately to the data attribute
- Parameters
function (Function) – Objective function to evaluate
f3dasm.optimization.gradient_based_algorithms module
- class f3dasm.optimization.gradient_based_algorithms.Adam(data: f3dasm.base.data.Data, hyperparameters: Optional[Mapping[str, Any]] = <factory>, seed: int = 81320, defaults: Optional[Mapping[str, Any]] = <factory>)
Bases:
f3dasm.base.optimization.OptimizerGradient-based Adam optimizer
- algorithm: Any
- data: f3dasm.base.data.Data
- defaults: Optional[Mapping[str, Any]]
- hyperparameters: Optional[Mapping[str, Any]]
- init_parameters()
Set the initialization parameters. This could be dynamic or static hyperparameters.
- update_step(function: f3dasm.base.function.Function) None
One iteration of the algorithm. Adds the new input vector and resulting output immediately to the data attribute
- Parameters
function (Function) – Objective function to evaluate
- class f3dasm.optimization.gradient_based_algorithms.Momentum(data: f3dasm.base.data.Data, hyperparameters: Optional[Mapping[str, Any]] = <factory>, seed: int = 81320, defaults: Optional[Mapping[str, Any]] = <factory>)
Bases:
f3dasm.base.optimization.OptimizerGradient-based Momentum optimizer
- algorithm: Any
- data: f3dasm.base.data.Data
- defaults: Optional[Mapping[str, Any]]
- hyperparameters: Optional[Mapping[str, Any]]
- init_parameters()
Set the initialization parameters. This could be dynamic or static hyperparameters.
- update_step(function: f3dasm.base.function.Function) None
One iteration of the algorithm. Adds the new input vector and resulting output immediately to the data attribute
- Parameters
function (Function) – Objective function to evaluate
- class f3dasm.optimization.gradient_based_algorithms.RandomSearch(data: f3dasm.base.data.Data, hyperparameters: Optional[Mapping[str, Any]] = <factory>, seed: int = 81320, defaults: Optional[Mapping[str, Any]] = <factory>)
Bases:
f3dasm.base.optimization.OptimizerNaive random search
- algorithm: Any
- data: f3dasm.base.data.Data
- defaults: Optional[Mapping[str, Any]]
- hyperparameters: Optional[Mapping[str, Any]]
- update_step(function: f3dasm.base.function.Function) None
One iteration of the algorithm. Adds the new input vector and resulting output immediately to the data attribute
- Parameters
function (Function) – Objective function to evaluate
- class f3dasm.optimization.gradient_based_algorithms.SGD(data: f3dasm.base.data.Data, hyperparameters: Optional[Mapping[str, Any]] = <factory>, seed: int = 81320, defaults: Optional[Mapping[str, Any]] = <factory>)
Bases:
f3dasm.base.optimization.OptimizerGradient-based Stochastig Gradient Descent (SGD) optimizer
- algorithm: Any
- data: f3dasm.base.data.Data
- defaults: Optional[Mapping[str, Any]]
- hyperparameters: Optional[Mapping[str, Any]]
- init_parameters()
Set the initialization parameters. This could be dynamic or static hyperparameters.
- update_step(function: f3dasm.base.function.Function) None
One iteration of the algorithm. Adds the new input vector and resulting output immediately to the data attribute
- Parameters
function (Function) – Objective function to evaluate