tf.keras.optimizers.legacy.Nadam

Optimizer that implements the NAdam algorithm.

Inherits From: Nadam, Optimizer

tf.keras.optimizers.legacy.Nadam(
    learning_rate=0.001,
    beta_1=0.9,
    beta_2=0.999,
    epsilon=1e-07,
    name='Nadam',
    **kwargs
)

Much like Adam is essentially RMSprop with momentum, Nadam is Adam with Nesterov momentum.

learning_rate A Tensor or a floating point value. The learning rate.
beta_1 A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.
beta_2 A float value or a constant float tensor. The exponential decay rate for the exponentially weighted infinity norm.
epsilon A small constant for numerical stability.
name Optional name for the operations created when applying gradients. Defaults to "Nadam".
**kwargs keyword arguments. Allowed arguments are clipvalue, clipnorm, global_clipnorm. If clipvalue (float) is set, the gradient of each weight is clipped to be no higher than this value. If clipnorm (float) is set, the gradient of each weight is individually clipped so that its norm is no higher than this value. If global_clipnorm (float) is set the gradient of all weights is clipped so that their global norm is no higher than this value. 

>>> opt = tf.keras.optimizers.Nadam(learning_rate=0.2)
>>> var1 = tf.Variable(10.0)
>>> loss = lambda: (var1 ** 2) / 2.0
>>> step_count = opt.minimize(loss, [var1]).numpy()
>>> "{:.1f}".format(var1.numpy())
9.8

ValueError in case of any invalid argument.