GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium.
Martin HeuselHubert RamsauerThomas UnterthinerBernhard NesslerGünter KlambauerSepp HochreiterPublished in: CoRR (2017)
Keyphrases
- nash equilibrium
- update rule
- game theory
- game theoretic
- ant colony optimization algorithm
- fixpoint
- variational inequalities
- learning rate
- mixed strategy
- nash equilibria
- pure strategy
- worst case
- learning algorithm
- cooperative
- traveling salesman problem
- negative matrix factorization
- incomplete information
- swarm intelligence
- upper bound
- training set
- multi agent systems