Global Convergence to the Equilibrium of GANs using Variational Inequalities
arXiv: Learning, Volume abs/1808.01531, 2018.
In optimization, the negative gradient of a function denotes the direction of steepest descent. Furthermore, traveling in any direction orthogonal to the gradient maintains the value of the function. In this work, we show that these orthogonal directions that are ignored by gradient descent can be critical in equilibrium problems. Equilib...More
PPT (Upload PPT)