tf.keras.optimizers.legacy.Adagrad

Optimizer that implements the Adagrad algorithm.

Inherits From: Adagrad, Optimizer

tf.keras.optimizers.legacy.Adagrad(
    learning_rate=0.001,
    initial_accumulator_value=0.1,
    epsilon=1e-07,
    name='Adagrad',
    **kwargs
)

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.

learning_rate Initial value for the learning rate: either a floating point value, or a tf.keras.optimizers.schedules.LearningRateSchedule instance. 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 used to maintain numerical stability.
name Optional name prefix for the operations created when applying gradients. Defaults to "Adagrad".
**kwargs keyword arguments. Allowed arguments are clipvalue, clipnorm, global_clipnorm. If clipvalue (float) is set, the gradient of each weight is clipped to be no higher than this value. If clipnorm (float) is set, the gradient of each weight is individually clipped so that its norm is no higher than this value. If global_clipnorm (float) is set the gradient of all weights is clipped so that their global norm is no higher than this value..

ValueError in case of any invalid argument.