DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914928818913280 |
|---|---|
| author | Du, Kai Xie, Yongle Zhou, Tao Zhou, Yuancheng |
| author_facet | Du, Kai Xie, Yongle Zhou, Tao Zhou, Yuancheng |
| contents | Sequential propagation of chaos (SPoC) is a recently developed tool to solve mean-field stochastic differential equations and their related nonlinear Fokker-Planck equations. Based on the theory of SPoC, we present a new method (deepSPoC) that combines the interacting particle system of SPoC and deep learning. Under the framework of deepSPoC, two classes of frequently used deep models include fully connected neural networks and normalizing flows are considered. For high-dimensional problems, spatial adaptive method are designed to further improve the accuracy and efficiency of deepSPoC. We analysis the convergence of the framework of deepSPoC under some simplified conditions and also provide a posterior error estimation for the algorithm. Finally, we test our methods on a wide range of different types of mean-field equations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16403 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos Du, Kai Xie, Yongle Zhou, Tao Zhou, Yuancheng Machine Learning Sequential propagation of chaos (SPoC) is a recently developed tool to solve mean-field stochastic differential equations and their related nonlinear Fokker-Planck equations. Based on the theory of SPoC, we present a new method (deepSPoC) that combines the interacting particle system of SPoC and deep learning. Under the framework of deepSPoC, two classes of frequently used deep models include fully connected neural networks and normalizing flows are considered. For high-dimensional problems, spatial adaptive method are designed to further improve the accuracy and efficiency of deepSPoC. We analysis the convergence of the framework of deepSPoC under some simplified conditions and also provide a posterior error estimation for the algorithm. Finally, we test our methods on a wide range of different types of mean-field equations. |
| title | DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.16403 |