f3dasm_optimize.sgd

sgd(learning_rate=0.01, momentum=0.0, nesterov=False, seed=None, **kwargs)

Stochastic Gradient Descent (SGD) optimizer. Adapted from the Optax library.

Parameters:

• learning_rate (float, optional) – The learning rate, by default 0.01.

• momentum (float, optional) – Momentum parameter, by default 0.0.

• nesterov (bool, optional) – Use Nesterov momentum, by default False.

• seed (int, optional) – Random seed, by default None.

Returns:

Optimizer object.

Return type:

Optimizer