Wasserstein GAN (WGAN)

As explained in the previous section, one of the most difficult problems with standard GANs is caused by the loss function based on the Jensen-Shannon divergence, whose value becomes constant when two distributions have disjointed supports. This situation is quite common with high-dimensional, semantically structured datasets. For example, images are constrained to having particular features in order to represent a specific subject (this is a consequence of the manifold assumption discussed in Chapter 2, Introduction to Semi-Supervised Learning). The initial generator distribution is very unlikely to overlap a true dataset, and in many cases, they are also very far from each other. This condition increases the risk of learning a wrong representation (a problem known as mode collapse), even when the discriminator is able to distinguish between true and generated...