tff.learning.optimizers.build_sgdm

Stay organized with collections Save and categorize content based on your preferences.

Returns a tff.learning.optimizers.Optimizer for momentum SGD.

tff.learning.optimizers.build_sgdm(
    learning_rate: float = 0.01, momentum: Optional[float] = None
) -> tff.learning.optimizers.Optimizer

Used in the notebooks

Used in the tutorials

This class supports the simple gradient descent and its variant with momentum.

If momentum is not used, the update rule given learning rate lr, weights w and gradients g is:

w = w - lr * g

If momentum m (a float between 0.0 and 1.0) is used, the update rule is

v = m * v + g
w = w - lr * v

where v is the velocity from previous steps of the optimizer.

learning_rate A positive float for learning rate, default to 0.01.
momentum A float between 0.0 and 1.0 for momentum.