Reviews: PacGAN: The power of two samples in generative adversarial networks

Summary: While Generative Adversarial Networks (GANs) have become the desired choice for generative tasks in the community, they also suffer from a nagging issue of mode collapse (cf. The current literature also has some empirical ways to handle this issue (cf. They present the technique of packing, in which the discriminator now uses multiple samples in its task. Detailed Comments: Clarity: The paper is very well written, both rigor and intuitive expositions are presented. Originality: As explained above in summary, perhaps this is the first time a framework of mode collapse is constructed and its theoretical underpinnings are discussed.