Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN

Authors

Paul Valsecchi Oliva
Yue Wu
Cuiyu He, The University of Texas Rio Grande Valley
Hao Ni

Document Type

Article

Publication Date

8-15-2022

Abstract

Due to the curse of dimensionality, solving high dimensional parabolic partial differential equations (PDEs) has been a challenging problem for decades. Recently, a weak adversarial network (WAN) proposed in Zang et al. (2020)[17] offered a flexible and computationally efficient approach to tackle this problem defined on arbitrary domains by leveraging the weak solution. WAN reformulates the PDE problem as a generative adversarial network, where the weak solution (primal network) and the test function (adversarial network) are parameterized by the multi-layer deep neural networks (DNNs). However, it is not yet clear whether DNNs are the most effective model for the parabolic PDE solutions as they do not take into account the fundamentally different roles played by time and spatial variables in the solution. To reinforce the difference, we design a novel so-called XNODE model for the primal network, which is built on the neural ODE (NODE) model with additional spatial dependency to incorporate the a priori information of the PDEs and serve as a universal and effective approximation to the solution. The proposed hybrid method (XNODE-WAN), by integrating the XNODE model within the WAN framework, leads to significant improvement in the performance and efficiency of training. Numerical results show that our method can reduce the training time to a fraction of that of the WAN model.

Comments

© 2022 The Author(s). Published by Elsevier Inc.

Recommended Citation

Oliva, Paul Valsecchi, et al. "Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN." Journal of Computational Physics 463 (2022): 111233. https://doi.org/10.1016/j.jcp.2022.111233

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Publication Title

Journal of Computational Physics

DOI

10.1016/j.jcp.2022.111233