On the Implicit Assumptions of GANs

Generative adversarial nets (GANs) (Goodfellow et al., 2014; Gutmann et al., 2014) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees.A number of enlightening papers, e.g.: (Arora et al., 2017; Sinn & Rawat, 2017; Cornish et al., 2018), have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years. We believe the identified problems deservemore attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models. We recently proposed analternative method (Li & Malik, 2018) that sidesteps these problems.