tf.keras.optimizers.Nadam

TensorFlow 1 version

View source on GitHub

Optimizer that implements the RMSprop algorithm.

Inherits From: Optimizer

View aliases

Main aliases

tf.optimizers.RMSprop

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.optimizers.RMSprop

tf.keras.optimizers.RMSprop(
    learning_rate=0.001, rho=0.9, momentum=0.0, epsilon=1e-07, centered=False,
    name='RMSprop', **kwargs
)

Used in the notebooks

Used in the guide	Used in the tutorials
Training and evaluation with the built-in methods The Functional API Mixed precision Writing your own callbacks	Parameter Server Training Transfer learning and fine-tuning Load NumPy data TensorFlow Federated for Image Classification Classifying CIFAR-10 with XLA

The gist of RMSprop is to:

Maintain a moving (discounted) average of the square of gradients
Divide the gradient by the root of this average

This implementation of RMSprop uses plain momentum, not Nesterov momentum.

The centered version additionally maintains a moving average of the gradients, and uses that average to estimate the variance.

Args
`learning_rate`	A `Tensor`, floating point value, or a schedule that is a `tf.keras.optimizers.schedules.LearningRateSchedule`, or a callable that takes no arguments and returns the actual value to use. The learning rate. Defaults to 0.001.
`rho`	Discounting factor for the history/coming gradient. Defaults to 0.9.
`momentum`	A scalar or a scalar `Tensor`. Defaults to 0.0.
`epsilon`	A small constant for numerical stability. This epsilon is "epsilon hat" in the Kingma and Ba paper (in the formula just before Section 2.1), not the epsilon in Algorithm 1 of the paper. Defaults to 1e-7.
`centered`	Boolean. If `True`, gradients are normalized by the estimated variance of the gradient; if False, by the uncentered second moment. Setting this to `True` may help with training, but is slightly more expensive in terms of computation and memory. Defaults to `False`.
`name`	Optional name prefix for the operations created when applying gradients. Defaults to `"RMSprop"`.
`**kwargs`	Keyword arguments. Allowed to be one of `"clipnorm"` or `"clipvalue"`. `"clipnorm"` (float) clips gradients by norm; `"clipvalue"` (float) clips gradients by value.

Note that in the dense implementation of this algorithm, variables and their corresponding accumulators (momentum, gradient moving average, square gradient moving average) will be updated even if the gradient is zero (i.e. accumulators will decay, momentum will be applied). The sparse implementation (used when the gradient is an IndexedSlices object, typically because of tf.gather or an embedding lookup in the forward pass) will not update variable slices or their accumulators unless those slices were used in the forward pass (nor is there an "eventual" correction to account for these omitted updates). This leads to more efficient updates for large embedding lookup tables (where most of the slices are not accessed in a particular graph execution), but differs from the published algorithm.

Usage:

opt = tf.keras.optimizers.RMSprop(learning_rate=0.1)
var1 = tf.Variable(10.0)
loss = lambda: (var1 ** 2) / 2.0    # d(loss) / d(var1) = var1
step_count = opt.minimize(loss, [var1]).numpy()
var1.numpy()
9.683772

Reference:

Hinton, 2012

TensorFlow

tf

tf.audio

tf.autograph

tf.bitwise

tf.compat

tf.config

tf.data

tf.debugging

tf.distribute

tf.dtypes

tf.errors

tf.estimator

tf.experimental

tf.feature_column

tf.graph_util

tf.image

tf.initializers

tf.io

tf.keras

tf.linalg

tf.lite

tf.lookup

tf.losses

tf.math

tf.metrics

tf.nest

tf.nn

tf.optimizers

tf.quantization

tf.queue

tf.ragged

tf.random

tf.raw_ops

tf.saved_model

tf.sets

tf.signal

tf.sparse

tf.strings

tf.summary

tf.sysconfig

tf.test

tf.tpu

tf.train

tf.version

tf.xla

tf.keras / optimizers / optimizers.Nadam

View aliases

Used in the notebooks

Args

Usage:

Reference: