On Convergence and Stability of GANs

05/19/2017 ∙ by Naveen Kodali, et al. ∙ 0

We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions. We analyze the convergence of GAN training from this new point of view to understand why mode collapse happens. We hypothesize the existence of undesirable local equilibria in this non-convex game to be responsible for mode collapse. We observe that these local equilibria often exhibit sharp gradients of the discriminator function around some real data points. We demonstrate that these degenerate local equilibria can be avoided with a gradient penalty scheme called DRAGAN. We show that DRAGAN enables faster training, achieves improved stability with fewer mode collapses, and leads to generator networks with better modeling performance across a variety of architectures and objective functions.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

page 11

page 12

page 13

page 14

Code Repositories

DRAGAN

A stable algorithm for GAN training


view repo

dragan-pytorch

PyTorch implementation of DRAGAN (https://arxiv.org/abs/1705.07215)


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.