TensorFlow · Method
tf.optimizers
tff.learning.optimizers.Optimizer describes iterative optimizers for TensorFlow Federated. It uses tensor state to carry values between steps instead of creating variables inside traced methods.
Last updated
Syntax
class Optimizer:
initialize(specs: Any) -> State
get_hparams(state: State) -> Hparams
next(...) -> StateIn-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.
SubscribeRelated
tff.learning.optimizers.build_sgdmtff.learning.optimizers.build_adamtff.learning.optimizers.schedule_learning_ratetff.learning.optimizers.LEARNING_RATE_KEY