Keras optimizers comparison on GAN
Tuning variables :
Learning rate is set to 0.002 and all the parameters are default. Trained with 2000 epochs and 256 batch size.
Optimizers will be compared are :
Stochastic gradient descent optimizer.
Includes support for momentum, learning rate decay, and Nesterov momentum.
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.
Adadelta is a more robust extension of Adagrad that adapts learning rates based on a moving window of gradient updates, instead of accumulating all past gradients. This way, Adadelta continues learning even when many updates have been done. Compared to Adagrad, in the original version of Adadelta you don’t have to set an initial learning rate. In this version, initial learning rate and decay factor can be set, as in most other Keras optimizers.
It is a variant of Adam based on the infinity norm.
Nesterov Adam optimizer.
Much like Adam is essentially RMSprop with momentum, Nadam is Adam RMSprop with Nesterov momentum.