Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.21213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908509371629568 |
|---|---|
| author | Su, Yun De Sterck, Hans Liu, Jun |
| author_facet | Su, Yun De Sterck, Hans Liu, Jun |
| contents | Leveraging a stochastic extension of Zubov's equation, we develop a physics-informed neural network (PINN) approach for learning a neural Lyapunov function that captures the largest probabilistic region of attraction (ROA) for stochastic systems. We then provide sufficient conditions for the learned neural Lyapunov functions that can be readily verified by satisfiability modulo theories (SMT) solvers, enabling formal verification of both local stability analysis and probabilistic ROA estimates. By solving Zubov's equation for the maximal Lyapunov function, our method provides more accurate and larger probabilistic ROA estimates than traditional sum-of-squares (SOS) methods. Numerical experiments on nonlinear stochastic systems validate the effectiveness of our approach in training and verifying neural Lyapunov functions for probabilistic stability analysis and ROA estimates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_21213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Verifying Probabilistic Regions of Attraction with Neural Lyapunov Functions for Stochastic Systems Su, Yun De Sterck, Hans Liu, Jun Optimization and Control Leveraging a stochastic extension of Zubov's equation, we develop a physics-informed neural network (PINN) approach for learning a neural Lyapunov function that captures the largest probabilistic region of attraction (ROA) for stochastic systems. We then provide sufficient conditions for the learned neural Lyapunov functions that can be readily verified by satisfiability modulo theories (SMT) solvers, enabling formal verification of both local stability analysis and probabilistic ROA estimates. By solving Zubov's equation for the maximal Lyapunov function, our method provides more accurate and larger probabilistic ROA estimates than traditional sum-of-squares (SOS) methods. Numerical experiments on nonlinear stochastic systems validate the effectiveness of our approach in training and verifying neural Lyapunov functions for probabilistic stability analysis and ROA estimates. |
| title | Verifying Probabilistic Regions of Attraction with Neural Lyapunov Functions for Stochastic Systems |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2508.21213 |