GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium.
Martin HeuselHubert RamsauerThomas UnterthinerBernhard NesslerSepp HochreiterPublished in: NIPS (2017)
Keyphrases
- nash equilibrium
- update rule
- game theory
- game theoretic
- nash equilibria
- ant colony optimization algorithm
- variational inequalities
- mixed strategy
- training set
- pure strategy
- fixpoint
- learning rate
- worst case
- multi agent systems
- learning algorithm
- ant colony optimization
- logic programs
- optimization problems
- knowledge representation
- stochastic gradient descent
- cooperative
- objective function