Skip to contents

Optimizer that implements the Adadelta algorithm.

Source: R/optimizers.R
optimizer_adadelta.Rd

Adadelta optimization is a stochastic gradient descent method that is based on adaptive learning rate per dimension to address two drawbacks:

  • The continual decay of learning rates throughout training.

  • The need for a manually selected global learning rate.

Adadelta is a more robust extension of Adagrad that adapts learning rates based on a moving window of gradient updates, instead of accumulating all past gradients. This way, Adadelta continues learning even when many updates have been done. Compared to Adagrad, in the original version of Adadelta you don't have to set an initial learning rate. In this version, the initial learning rate can be set, as in most other Keras optimizers.

Usage

optimizer_adadelta(
  learning_rate = 0.001,
  rho = 0.95,
  epsilon = 1e-07,
  weight_decay = NULL,
  clipnorm = NULL,
  clipvalue = NULL,
  global_clipnorm = NULL,
  use_ema = FALSE,
  ema_momentum = 0.99,
  ema_overwrite_frequency = NULL,
  name = "adadelta",
  ...,
  loss_scale_factor = NULL,
  gradient_accumulation_steps = NULL
)

Arguments

learning_rate

A float, a [LearningRateSchedule()] instance, or a callable that takes no arguments and returns the actual value to use. The learning rate. Defaults to 0.001. Note that Adadelta tends to benefit from higher initial learning rate values compared to other optimizers. To match the exact form in the original paper, use 1.0.

rho

A floating point value. The decay rate. Defaults to 0.95.

epsilon

Small floating point value for maintaining numerical stability.

weight_decay

Float. 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 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 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 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.

name

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

...

For forward/backward compatability.

loss_scale_factor

Float or NULL. If a float, the scale factor will be multiplied the loss before computing gradients, and the inverse of the scale factor will be multiplied by the gradients before updating variables. Useful for preventing underflow during mixed precision training. Alternately, optimizer_loss_scale() will automatically set a loss scale factor.

gradient_accumulation_steps

Int or NULL. If an int, model and optimizer variables will not be updated at every step; instead they will be updated every gradient_accumulation_steps steps, using the average value of the gradients since the last update. This is known as "gradient accumulation". This can be useful when your batch size is very small, in order to reduce gradient noise at each update step. EMA frequency will look at "accumulated" iterations value (optimizer steps // gradient_accumulation_steps). Learning rate schedules will look at "real" iterations value (optimizer steps).

Value

an Optimizer instance

Reference

See also

Other optimizers:
optimizer_adafactor()
optimizer_adagrad()
optimizer_adam()
optimizer_adam_w()
optimizer_adamax()
optimizer_ftrl()
optimizer_lamb()
optimizer_lion()
optimizer_loss_scale()
optimizer_nadam()
optimizer_rmsprop()
optimizer_sgd()