* This is an updated version of an ICML'17 paper with the same title.
The main difference is that in the ICML'17 version the pure equilibrium
result was only proved for Wasserstein GAN. In the current version the result
applies to most reasonable training objectives. In particular, Theorem 4.3
now applies to both original GAN and Wasserstein GAN Access Paper or Ask Questions
* Best paper in the NIPS 2016 Workshop on Nonconvex Optimization for
Machine Learning: Theory and Practice. In submission Access Paper or Ask Questions