Method __init__

Construct a new gradient descent optimizer with coupled adaptive batch size (CABS). Args: :learning_rate: A Tensor or a floating point value. The learning rate to use. :bs_min: Minimum batch size (integer). Defaults to 16. :bs_max: Maximum batch size (integer)

(self, learning_rate, bs_min=16, bs_max=2048,
               running_avg_constant=0.95, eps=0.0, c=1.0, debug=False,
               name="CABS-SGD")