ICML 2021spotlight7 citations

Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation

Sung Woo Park, Dong Wook Shu, Junseok Kwon

Abstract

In this paper, we present a novel generative adversarial network (GAN) that can describe Markovian temporal dynamics. To generate stochastic sequential data, we introduce a novel stochastic differential equation-based conditional generator and spatial-temporal constrained discriminator networks. To stabilize the learning dynamics of the min-max type of the GAN objective function, we propose well-posed constraint terms for both networks. We also propose a novel conditional Markov Wasserstein distance to induce a pathwise Wasserstein distance. The experimental results demonstrate that our method outperforms state-of-the-art methods using several different types of data.

BibTeX
@InProceedings{pmlr-v139-park21d,
  title = 	 {Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation},
  author =       {Park, Sung Woo and Shu, Dong Wook and Kwon, Junseok},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {8413--8421},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/park21d/park21d.pdf},
  url = 	 {https://proceedings.mlr.press/v139/park21d.html},
  abstract = 	 {In this paper, we present a novel generative adversarial network (GAN) that can describe Markovian temporal dynamics. To generate stochastic sequential data, we introduce a novel stochastic differential equation-based conditional generator and spatial-temporal constrained discriminator networks. To stabilize the learning dynamics of the min-max type of the GAN objective function, we propose well-posed constraint terms for both networks. We also propose a novel conditional Markov Wasserstein distance to induce a pathwise Wasserstein distance. The experimental results demonstrate that our method outperforms state-of-the-art methods using several different types of data.}
}