tidy3d.plugins.invdes.AdamOptimizer

class AdamOptimizer

Bases: AbstractOptimizer

Specification for an optimization.

Parameters:

• design (Union[InverseDesign, InverseDesignMulti]) – Specification describing the inverse design problem we wish to optimize.

• learning_rate (PositiveFloat) – Step size for the gradient descent optimizer.

• maximize (bool = True) – If True, the optimizer will maximize the objective function. If False, the optimizer will minimize the objective function.

• num_steps (PositiveInt) – Number of steps in the gradient descent optimizer.

• results_cache_fname (Optional[str] = None) – If specified, will save the optimization state to a local .pkl file using dill.dump(). This file stores an InverseDesignResult corresponding to the latest state of the optimization. To continue this run from the file using the same optimizer instance, call optimizer.complete_run_from_history(). Alternatively, the latest results can then be loaded with td.InverseDesignResult.from_file(fname) and then continued using optimizer.continue_run(result).

• store_full_results (bool = True) – If True, stores the full history for the vector fields, specifically the gradient, params, and optimizer state. For large design regions and many iterations, storing the full history of these fields can lead to large file size and memory usage. In some cases, we recommend setting this field to False, which will only store the last computed state of these variables.

• beta1 (float = 0.9) – Beta 1 parameter in the Adam optimization method.

• beta2 (float = 0.999) – Beta 2 parameter in the Adam optimization method.

• eps (PositiveFloat = 1e-08) – Epsilon parameter in the Adam optimization method.

Attributes

beta1
beta2
eps
design
learning_rate
maximize
num_steps
results_cache_fname
store_full_results

Methods

initial_state(parameters)	initial state of the optimizer
update(parameters, gradient[, state])

beta1

beta2

eps

initial_state(parameters)

initial state of the optimizer

update(parameters, gradient, state=None)