arXiv (Cornell University) · 2019 · 78 citations · 15 references
ComputingComputer ScienceMathematicsAlgorithmsGame TheoryMachine LearningAlgorithmic Game TheoryNash EquilibriumNetwork GamesZero-sum GamesAdversarial Game ModelsGenerative Adversarial NetworksNash Equilibrium ComputationNash Equilibrium ExistenceNon-stationary EquilibriumStationary PointsTwo-player GamesZero-sum Equilibrium
We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms cannot guarantee convergence to local Nash equilibria due to the existence of non-Nash stationary points. By taking advantage of the differential structure of the game, we construct an algorithm for which the local Nash equilibria are the only attracting fixed points. We also show that the algorithm exhibits no oscillatory behaviors in neighborhoods of equilibria and show that it has the same per-iteration complexity as other recently proposed algorithms. We conclude by validating the algorithm on two numerical examples: a toy example with multiple Nash equilibria and a non-Nash equilibrium, and the training of a small generative adversarial network (GAN).
15
Lars Mescheder, Sebastian Nowozin, Andreas Geiger · arXiv (Cornell University) · 2017 · 188 citations · Full text