Abstract
Why are Generative Adversarial Networks (GANs) so popular? What is the purpose of designing GANs? Can we justify functioning of GANs theoretically? How are the theoretical guarantees? Are there any shortcomings? With the popularity of GANs, the researchers across the globe have been perplexed by these questions. In the last year (2017), a plethora of research papers attempted to answer the above questions. In this article, we put in our best efforts to compare and contrast different results and put forth a summary of theoretical contributions about GANs with focus on image/visual applications. Our main aim is to highlight the primary issues related to GANs that each of these papers examine. Besides we provide insight into how each of the discussed articles solve the concerned problems. We expect this summary paper to give a bird’s eye view to a person wishing to understand the theory behind GANs.
Abstract (translated by Google)
URL
https://arxiv.org/abs/1804.00140