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

Sung Woo Park, Dong Wook Shu, Junseok Kwon
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8413-8421, 2021.

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 this Paper


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.} }
Endnote
%0 Conference Paper %T Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation %A Sung Woo Park %A Dong Wook Shu %A Junseok Kwon %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-park21d %I PMLR %P 8413--8421 %U https://proceedings.mlr.press/v139/park21d.html %V 139 %X 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.
APA
Park, S.W., Shu, D.W. & Kwon, J.. (2021). Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:8413-8421 Available from https://proceedings.mlr.press/v139/park21d.html.

Related Material