Documentation update to reference learning rate schedules in the optimizer documentation.

PiperOrigin-RevId: 281104367
Change-Id: Id814018dfb8f21b4d1b46b7d675838c56765b975

tensorflow/python/keras/optimizer_v2/adadelta.py

@@ -74,7 +74,8 @@ class Adadelta(optimizer_v2.OptimizerV2):
     learning rate can be set, as in most other Keras optimizers.
 
     Args:
-      learning_rate: A `Tensor` or a floating point value. The learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
         To match the exact form in the original paper use 1.0.
       rho: A `Tensor` or a floating point value. The decay rate.
       epsilon: A `Tensor` or a floating point value.  A constant epsilon used

tensorflow/python/keras/optimizer_v2/adagrad.py

@@ -63,7 +63,8 @@ class Adagrad(optimizer_v2.OptimizerV2):
     """Construct a new Adagrad optimizer.
 
     Args:
-      learning_rate: A `Tensor` or a floating point value.  The learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       initial_accumulator_value: A floating point value.
         Starting value for the accumulators, must be non-negative.
       epsilon: A small floating point value to avoid zero denominator.

tensorflow/python/keras/optimizer_v2/adam.py

@@ -108,7 +108,8 @@ class Adam(optimizer_v2.OptimizerV2):
     unless a variable slice was actually used).
 
     Args:
-      learning_rate: A Tensor or a floating point value.  The learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       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

tensorflow/python/keras/optimizer_v2/adamax.py

@@ -83,7 +83,8 @@ class Adamax(optimizer_v2.OptimizerV2):
     used).
 
     Args:
-      learning_rate: A Tensor or a floating point value.  The learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       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

tensorflow/python/keras/optimizer_v2/ftrl.py

@@ -66,7 +66,8 @@ class Ftrl(optimizer_v2.OptimizerV2):
     r"""Construct a new FTRL optimizer.
 
     Args:
-      learning_rate: A float value or a constant float `Tensor`.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       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.

tensorflow/python/keras/optimizer_v2/gradient_descent.py

@@ -69,7 +69,8 @@ class SGD(optimizer_v2.OptimizerV2):
     """Construct a new Stochastic Gradient Descent or Momentum optimizer.
 
     Arguments:
-      learning_rate: float hyperparameter >= 0. Learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       momentum: float hyperparameter >= 0 that accelerates SGD in the relevant
         direction and dampens oscillations.
       nesterov: boolean. Whether to apply Nesterov momentum.

tensorflow/python/keras/optimizer_v2/rmsprop.py

@@ -83,7 +83,8 @@ class RMSprop(optimizer_v2.OptimizerV2):
     a particular graph execution), but differs from the published algorithm.
 
     Args:
-      learning_rate: A Tensor or a floating point value.  The learning rate.
+      learning_rate: A `Tensor`, floating point value, or a schedule that is a
+        `tf.keras.optimizers.schedules.LearningRateSchedule`. The learning rate.
       rho: Discounting factor for the history/coming gradient
       momentum: A scalar tensor.
       epsilon: Small value to avoid zero denominator.