Corpus ID: 21082355

Linking Generative Adversarial Learning and Binary Classification

@article{Balsubramani2017LinkingGA,
  title={Linking Generative Adversarial Learning and Binary Classification},
  author={A. Balsubramani},
  journal={ArXiv},
  year={2017},
  volume={abs/1709.01509}
}
In this note, we point out a basic link between generative adversarial (GA) training and binary classification -- any powerful discriminator essentially computes an (f-)divergence between real and generated samples. The result, repeatedly re-derived in decision theory, has implications for GA Networks (GANs), providing an alternative perspective on training f-GANs by designing the discriminator loss function. 

References

SHOWING 1-9 OF 9 REFERENCES
Generative Adversarial Nets
Information, Divergence and Risk for Binary Experiments
On Divergences and Informations in Statistics and Information Theory
  • F. Liese, I. Vajda
  • Mathematics, Computer Science
  • IEEE Transactions on Information Theory
  • 2006
Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
Generative adversarial nets On divergences and informations in statistics and information theory
  • IEEE Transactions on Information Theory