Generative Adversarial Networks as Variational Training of Energy Based Models (VGAN)

In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density is approximated by a variational distribution that is easy to sample from. The training of VGA...More