Corpus ID: 60440543

(q, p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs

@article{Mallasto2019qPG,
  title={(q, p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs},
  author={Anton Mallasto and J. Frellsen and W. Boomsma and A. Feragen},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.03642}
}
Generative Adversial Networks (GANs) have made a major impact in computer vision and machine learning as generative models. Wasserstein GANs (WGANs) brought Optimal Transport (OT) theory into GANs, by minimizing the $1$-Wasserstein distance between model and data distributions as their objective function. Since then, WGANs have gained considerable interest due to their stability and theoretical framework. We contribute to the WGAN literature by introducing the family of $(q,p)$-Wasserstein GANs… Expand
3 Citations
How Well Do WGANs Estimate the Wasserstein Metric?
  • 6
  • PDF
Entropy-Regularized 2-Wasserstein Distance between Gaussian Measures
  • 7
  • PDF
Learning normalizing flows from Entropy-Kantorovich potentials
  • 2
  • PDF

References

SHOWING 1-10 OF 27 REFERENCES
Wasserstein Divergence for GANs
  • 52
  • PDF
Generative Modeling Using the Sliced Wasserstein Distance
  • 78
  • PDF
Improved Training of Wasserstein GANs
  • 4,080
  • PDF
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
  • 2,521
  • Highly Influential
  • PDF
Wasserstein Auto-Encoders
  • 416
  • PDF
Improved Techniques for Training GANs
  • 4,172
  • PDF
Sinkhorn-AutoDiff: Tractable Wasserstein Learning of Generative Models
  • 49
Generative Adversarial Nets
  • 21,528
  • PDF
Learning Generative Models with Sinkhorn Divergences
  • 237
  • PDF
Spectral Normalization for Generative Adversarial Networks
  • 1,852
  • PDF
...
1
2
3
...