optimizer_adagrad: Optimizer that implements the Adagrad algorithm.

In rstudio/keras: R Interface to 'Keras'

Optimizer that implements the Adagrad algorithm.

Description

Adagrad is an optimizer with parameter-specific learning rates, which are adapted relative to how frequently a parameter gets updated during training. The more updates a parameter receives, the smaller the updates.

Usage

optimizer_adagrad(
  learning_rate = 0.001,
  initial_accumulator_value = 0.1,
  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 = "adagrad",
  ...,
  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 Adagrad 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.
initial_accumulator_value	Floating point value. Starting value for the accumulators (per-parameter momentum values). Must be non-negative.
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 & 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.

Value

an Optimizer instance

Reference

• Duchi et al., 2011.

See Also

• https://keras.io/api/optimizers/adagrad#adagrad-class

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

rstudio/keras documentation built on April 17, 2024, 5:37 p.m.