Approximate Last Iterate Convergence in Overparameterized GANs
Elbert Du · arXiv (Cornell University) · 2021
In this work, we showed that the Implicit Update and Predictive Methods dynamics introduced in prior work satisfy last iterate convergence to a neighborhood around the optimum in overparameterized GANs, where the size of the neighborhood shrinks with the width of the neural network. This is in contrast to prior results, which only guaranteed average iterate convergence.