Timezone: »

Generalization and Equilibrium in Generative Adversarial Nets (GANs)
Sanjeev Arora · Rong Ge · Yingyu Liang · Tengyu Ma · Yi Zhang

Sun Aug 08:30 PM -- 08:48 PM PDT @ Parkside 1

It is shown 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 natural training objective (Wasserstein) 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.

Author Information

Sanjeev Arora (Princeton University)
Rong Ge (Duke University)
Yingyu Liang (Princeton University)
Tengyu Ma (Princeton University)
Yi Zhang (Princeton University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors