optimizer_adamax: Optimizer that implements the Adamax algorithm

View source: R/optimizers.R

optimizer_adamaxR Documentation

Optimizer that implements the Adamax algorithm

Description

Optimizer that implements the Adamax algorithm

Usage

optimizer_adamax(
  learning_rate = 0.001,
  beta_1 = 0.9,
  beta_2 = 0.999,
  epsilon = 1e-07,
  weight_decay = NULL,
  clipnorm = NULL,
  clipvalue = NULL,
  global_clipnorm = NULL,
  use_ema = FALSE,
  ema_momentum = 0.99,
  ema_overwrite_frequency = NULL,
  jit_compile = TRUE,
  name = "Adamax",
  ...
)

Arguments

learning_rate

A tf.Tensor, floating point value, 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.

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.

weight_decay

Float, defaults to NULL. If set, weight decay is applied.

clipnorm

Float. If set, the gradient of each weight is individually clipped so that its norm is no higher than this value.

clipvalue

Float. If set, the gradient of each weight is clipped to be no higher than this value.

global_clipnorm

Float. If set, the gradient of all weights is clipped so that their global norm is no higher than this value.

use_ema

Boolean, defaults to FALSE. If TRUE, exponential moving average (EMA) is applied. EMA consists of computing an exponential moving average of the weights of the model (as the weight values change after each training batch), and periodically overwriting the weights with their moving average.

ema_momentum

Float, defaults to 0.99. Only used if use_ema=TRUE. This is # noqa: E501 the momentum to use when computing the EMA of the model's weights: new_average = ema_momentum * old_average + (1 - ema_momentum) * current_variable_value.

ema_overwrite_frequency

Int or NULL, defaults to NULL. Only used if use_ema=TRUE. Every ema_overwrite_frequency steps of iterations, we overwrite the model variable by its moving average. If NULL, the optimizer # noqa: E501 does not overwrite model variables in the middle of training, and you need to explicitly overwrite the variables at the end of training by calling optimizer.finalize_variable_values() (which updates the model # noqa: E501 variables in-place). When using the built-in fit() training loop, this happens automatically after the last epoch, and you don't need to do anything.

jit_compile

Boolean, defaults to TRUE. If TRUE, the optimizer will use XLA # noqa: E501 compilation. If no GPU device is found, this flag will be ignored.

name

String. The name to use for momentum accumulator weights created by the optimizer.

...

Used for backward and forward compatibility

Details

Adamax, a variant of Adam based on the infinity norm, is a first-order gradient-based optimization method. Due to its capability of adjusting the learning rate based on data characteristics, it is suited to learn time-variant process, e.g., speech data with dynamically changed noise conditions. Default parameters follow those provided in the paper (see references below).

Initialization:

m = 0  # Initialize initial 1st moment vector
u = 0  # Initialize the exponentially weighted infinity norm
t = 0  # Initialize timestep

The update rule for parameter w with gradient g is described at the end of section 7.1 of the paper (see the referenece section):

t += 1
m = beta1 * m + (1 - beta) * g
u = max(beta2 * u, abs(g))
current_lr = learning_rate / (1 - beta1 ** t)
w = w - current_lr * m / (u + epsilon)

Value

Optimizer for use with compile.keras.engine.training.Model.

See Also

Other optimizers: optimizer_adadelta(), optimizer_adagrad(), optimizer_adam(), optimizer_ftrl(), optimizer_nadam(), optimizer_rmsprop(), optimizer_sgd()


keras documentation built on Aug. 16, 2023, 1:07 a.m.