A Deep Ritz Method for High-Dimensional Steady States of the Cahn-Hilliard Equation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910251957092352 |
|---|---|
| author | Liu, Yi Gu, Shuting |
| author_facet | Liu, Yi Gu, Shuting |
| contents | The Cahn-Hilliard equation is a fundamental model for describing phase separation phenomena in binary mixtures. Traditional numerical methods, such as finite difference and finite element methods, often incur substantial computational cost, particularly when computing steady-state solutions in high-dimensional settings. To address this challenge, we propose a deep learning-based framework -- the Deep Ritz method -- for computing steady states of the Cahn-Hilliard equation under periodic boundary conditions. An enhanced augmented Lagrangian formulation is incorporated to strictly enforce the mass conservation constraint, while separable Fourier feature mappings are employed to naturally encode periodicity and enhance the representation of nontrivial solution structures. The proposed method exhibits a notable dual capability: it not only achieves fast convergence to steady states but also effectively identifies multiple nontrivial solutions corresponding to different local minimizers of the energy functional. Extensive numerical experiments in one-, two-, and three-dimensional cases demonstrate that the method can successfully capture a rich variety of phase separation patterns, including droplet-type, lamellar, and tubular structures. We also compare the numerical results with those computed by finite difference method (FDM) for one- and two-dimensional cases, highlighting the effectiveness and robustness of the proposed approach in exploring complex high-dimensional energy landscapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17772 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Deep Ritz Method for High-Dimensional Steady States of the Cahn-Hilliard Equation Liu, Yi Gu, Shuting Numerical Analysis The Cahn-Hilliard equation is a fundamental model for describing phase separation phenomena in binary mixtures. Traditional numerical methods, such as finite difference and finite element methods, often incur substantial computational cost, particularly when computing steady-state solutions in high-dimensional settings. To address this challenge, we propose a deep learning-based framework -- the Deep Ritz method -- for computing steady states of the Cahn-Hilliard equation under periodic boundary conditions. An enhanced augmented Lagrangian formulation is incorporated to strictly enforce the mass conservation constraint, while separable Fourier feature mappings are employed to naturally encode periodicity and enhance the representation of nontrivial solution structures. The proposed method exhibits a notable dual capability: it not only achieves fast convergence to steady states but also effectively identifies multiple nontrivial solutions corresponding to different local minimizers of the energy functional. Extensive numerical experiments in one-, two-, and three-dimensional cases demonstrate that the method can successfully capture a rich variety of phase separation patterns, including droplet-type, lamellar, and tubular structures. We also compare the numerical results with those computed by finite difference method (FDM) for one- and two-dimensional cases, highlighting the effectiveness and robustness of the proposed approach in exploring complex high-dimensional energy landscapes. |
| title | A Deep Ritz Method for High-Dimensional Steady States of the Cahn-Hilliard Equation |
| topic | Numerical Analysis |
| url | https://arxiv.org/abs/2604.17772 |