authors: Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma
journal: (ICML 2014)
publication year: 2014
links: arxiv (preprint)

abstract: We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is also shown that an approximate pure equilibrium exists in the discriminator/generator game for a special class of generators with natural training objectives when generator capacity and training set sizes are moderate. This existence of equilibrium inspires MIX+GAN protocol, which can be combined with any existing GAN training, and empirically shown to improve some of them.

Category: Paper Announcements