Linking Generative Adversarial Learning and Binary Classification

Akshay Balsubramani

Linking Generative Adversarial Learning and Binary Classification

Machine Learning 2017-09-06 v1 Artificial Intelligence Machine Learning

Authors: Akshay Balsubramani

Abstract

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.

Keywords

generative adversarial network

Cite

@article{arxiv.1709.01509,
  title  = {Linking Generative Adversarial Learning and Binary Classification},
  author = {Akshay Balsubramani},
  journal= {arXiv preprint arXiv:1709.01509},
  year   = {2017}
}

Related papers

View all related →

Machine Learning · Statistics

Boundary-Seeking Generative Adversarial Networks

R Devon Hjelm, Athul Paul Jacob, Tong Che, Adam Trischler +2