tf.keras.optimizers.SGD | TensorFlow Core v2.7.0
www.tensorflow.org › tf › kerasFederated Learning for Image Classification. Update rule for parameter w with gradient g when momentum is 0: w = w - learning_rate * g. Update rule when momentum is larger than 0: velocity = momentum * velocity - learning_rate * g w = w + velocity. When nesterov=True, this rule becomes: velocity = momentum * velocity - learning_rate * g w = w ...
SGD - Keras
keras.io › api › optimizerslearning_rate: A Tensor, floating point value, or 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 0.01.