* 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
* 19 pages, 9 figures, in submission to NeuroImage. Prior version
presented at MLINI-2016 workshop, 2016 (arXiv:1701.01437) and ICML 2016
Workshop on Multi-view Representation Learning Access Paper or Ask Questions