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

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.

Cite

Text

Park et al. "Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation." International Conference on Machine Learning, 2021.

Markdown

[Park et al. "Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/park2021icml-generative/)

BibTeX

@inproceedings{park2021icml-generative,
  title     = {{Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation}},
  author    = {Park, Sung Woo and Shu, Dong Wook and Kwon, Junseok},
  booktitle = {International Conference on Machine Learning},
  year      = {2021},
  pages     = {8413-8421},
  volume    = {139},
  url       = {https://mlanthology.org/icml/2021/park2021icml-generative/}
}