On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classification. (arXiv:1901.08753v3 [cs.LG] UPDATED)

Recent years have seen adversarial losses been applied to many fields. Their
applications extend beyond the originally proposed generative modeling to
conditional generative and discriminative settings. While prior work has
proposed various output activation functions and regularization approaches,
some open questions still remain unanswered. In this paper, we aim to study the
following two research questions: 1) What types of output activation functions
form a well-behaved adversarial loss? 2) How different combinations of output
activation functions and regularization approaches perform …

analysis arxiv classification divergence losses mnist study