Reparameterized Sampling for Generative Adversarial Networks

Abstract

Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sample efficiency because of the independent proposal sampling from the generator. In this work, we propose REP-GAN, a novel sampling method that allows general dependent proposals by REParameterizing the Markov chains into the latent space of the generator. Theoretically, we show that our reparameterized proposal admits a closed-form Metropolis-Hastings acceptance ratio. Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.

Cite

Text

Wang et al. "Reparameterized Sampling for Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021. doi:10.1007/978-3-030-86523-8_30

Markdown

[Wang et al. "Reparameterized Sampling for Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.](https://mlanthology.org/ecmlpkdd/2021/wang2021ecmlpkdd-reparameterized/) doi:10.1007/978-3-030-86523-8_30

BibTeX

@inproceedings{wang2021ecmlpkdd-reparameterized,
  title     = {{Reparameterized Sampling for Generative Adversarial Networks}},
  author    = {Wang, Yifei and Wang, Yisen and Yang, Jiansheng and Lin, Zhouchen},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2021},
  pages     = {494-509},
  doi       = {10.1007/978-3-030-86523-8_30},
  url       = {https://mlanthology.org/ecmlpkdd/2021/wang2021ecmlpkdd-reparameterized/}
}