Let us assume we have a GRU network containing $H$ layers to process a training dataset with $K$ tuples, $I$ features, and $H_i$ nodes in each layer.
I have a pretty basic idea how the complexity of algorithms are calculated, however, with the presence of multiple factors that affect the performance of a GRU network including the number of layers, the amount of training data (which needs to be large), number of units in each layer, epochs and maybe regularization techniques, training with back-propagation through time, I am messed up. I have found an intriguing answer for neural networks complexity out here What is the time complexity for training a neural network using back-propagation?, but that was not enough to clear my doubt.
So, what is the time complexity of the algorithm, which uses back-propagation through time, to train GRU networks?
