Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks

@article{Liang2018InteractionMA,
  title={Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks},
  author={Tengyuan Liang and James Stokes},
  journal={CoRR},
  year={2018},
  volume={abs/1802.06132}
}
Motivated by the pursuit of a systematic computational and algorithmic understanding of Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic local convergence theory for smooth two-player games, which subsumes several discrete-time gradientbased saddle point dynamics. The analysis reveals the surprising nature of the off-diagonal interaction term as both a blessing and a curse. On the one hand, this interaction term explains the origin of the slow-down effect… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 11 times over the past 90 days. VIEW TWEETS

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…