tf.keras.optimizers.experimental.Ftrl

Optimizer that implements the FTRL algorithm.

Inherits From: Optimizer

"Follow The Regularized Leader" (FTRL) is an optimization algorithm developed at Google for click-through rate prediction in the early 2010s. It is most suitable for shallow models with large and sparse feature spaces. The algorithm is described by McMahan et al., 2013. The Keras version has support for both online L2 regularization (the L2 regularization described in the paper above) and shrinkage-type L2 regularization (which is the addition of an L2 penalty to the loss function).

Initialization:

n = 0
sigma = 0
z = 0

Update rule for one variable w:

prev_n = n
n = n + g ** 2
sigma = (n ** -lr_power - prev_n ** -lr_power) / lr
z = z + g - sigma * w
if abs(z) < lambda_1:
  w = 0
else:
  w = (sgn(z) * lambda_1 - z) / ((beta + sqrt(n)) / alpha + lambda_2)

Notation:

  • lr is the learning rate
  • g is the gradient for the variable
  • lambda_1 is the L1 regularization strength
  • lambda_2 is the L2 regularization strength
  • lr_power is the power to scale n.

Check the documentation for the l2_shrinkage_regularization_strength parameter for more details when shrinkage is enabled, in which case gradient is replaced with a gradient with shrinkage.

learning_rate A 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.
learning_rate_power A float value, must be less or equal to zero. Controls how the learning rate decreases during training. Use zero for a fixed learning rate.
initial_accumulator_value The starting value for accumulators. Only zero or positive values are allowed.
l1_regularization_strength A float value, must be greater than or equal to zero. Defaults to 0.0.
l2_regularization_strength A float value, must be greater than or equal to zero. Defaults to 0.0.
l2_shrinkage_regularization_strength A float value, must be greater than or equal to zero. This differs from L2 above in that the L2 above is a stabilization penalty, whereas this L2 shrinkage is a magnitude penalty. When input is sparse shrinkage will only happen on the active weights.
beta A float value, representing the beta value from the paper. Defaults to 0.0.
name String. The name to use for momentum accumulator weights created by the optimizer.
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 None, defaults to None. Only used if use_ema=True. Every ema_overwrite_frequency steps of iterations, we overwrite the model variable by its moving average. If None, 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.
**kwargs keyword arguments only used for backward compatibility.

iterations The number of training steps this optimizer has run.

By default, iterations would be incremented by one every time apply_gradients() is called.

learning_rate

Methods

add_variable

View source

Create an optimizer variable.

Args
shape A list of integers, a tuple of integers, or a 1-D Tensor of type int32. Defaults to scalar if unspecified.
dtype The DType of the optimizer variable to be created. Defaults to tf.keras.backend.floatx if unspecified.
initializer string or callable. Initializer instance.
name The name of the optimizer variable to be created.

Returns
An optimizer variable, in the format of tf.Variable.

add_variable_from_reference

View source

Create an optimizer variable from model variable.

Create an optimizer variable based on the information of model variable. For example, in SGD optimizer momemtum, for each model variable, a corresponding momemtum variable is created of the same shape and dtype.

Args
model_variable tf.Variable. The corresponding model variable to the optimizer variable to be created.
variable_name String. The name prefix of the optimizer variable to be created. The create variables name will follow the pattern {variable_name}/{model_variable.name}, e.g., momemtum/dense_1.
shape List or Tuple, defaults to None. The shape of the optimizer variable to be created. If None, the created variable will have the same shape as model_variable.
initial_value A Tensor, or Python object convertible to a Tensor, defaults to None. The initial value of the optimizer variable, if None, the initial value will be default to 0.

Returns
An optimizer variable.

aggregate_gradients

View source

Aggregate gradients on all devices.

By default we will perform reduce_sum of gradients across devices. Users can implement their own aggregation logic by overriding this method.

Args
grads_and_vars List of (gradient, variable) pairs.

Returns
List of (gradient, variable) pairs.

apply_gradients

View source

Apply gradients to variables.

Args
grads_and_vars List of (gradient, variable) pairs.
skip_gradients_aggregation If true, gradients aggregation will not be performed inside optimizer. Usually this arg is set to True when you write custom code aggregating gradients outside the optimizer.

Returns
None

Raises
TypeError If grads_and_vars is malformed.
RuntimeError If called in a cross-replica context.

build

View source

Initialize optimizer variables.

Args
var_list list of model variables to build Ftrl variables on.

compute_gradients

View source

Compute gradients of loss on trainable variables.

Args
loss Tensor or callable. If a callable, loss should take no arguments and return the value to minimize.
var_list list or tuple of Variable objects to update to minimize loss.
tape (Optional) tf.GradientTape. If loss is provided as a Tensor, the tape that computed the loss must be provided.

Returns
A list of (gradient, variable) pairs. Variable is always present, but gradient can be None.

finalize_variable_values

View source

Set the final value of model's trainable variables.

Sometimes there are some extra steps before ending the variable updates, such as overriding the model variables with its average value.

Args
var_list list of model variables.

from_config

View source

Creates an optimizer from its config.

This method is the reverse of get_config, capable of instantiating the same optimizer from the config dictionary.

Args
config A Python dictionary, typically the output of get_config.

Returns
An optimizer instance.

get_config

View source

Returns the config of the optimizer.

An optimizer config is a Python dictionary (serializable) containing the configuration of an optimizer. The same optimizer can be reinstantiated later (without any saved state) from this configuration.

Subclass optimizer should override this method to include other hyperparameters.

Returns
Python dictionary.

minimize

View source

Minimize loss by updating var_list.

This method simply computes gradient using tf.GradientTape and calls apply_gradients(). If you want to process the gradient before applying then call tf.GradientTape and apply_gradients() explicitly instead of using this function.

Args
loss Tensor or callable. If a callable, loss should take no arguments and return the value to minimize.
var_list list or tuple of Variable objects to update to minimize loss.
tape (Optional) tf.GradientTape.

Returns
None

update_step

View source

Update step given gradient and the associated model variable.