Physics-Informed Neural Network Lyapunov Functions: PDE Characterization, Learning, and Verification

December 14, 2023 Β· Declared Dead Β· πŸ› at - Automatisierungstechnik

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jun Liu, Yiming Meng, Maxwell Fitzsimmons, Ruikun Zhou arXiv ID 2312.09131 Category math.OC: Optimization & Control Cross-listed cs.LG, eess.SY Citations 37 Venue at - Automatisierungstechnik Last Checked 6 months ago
Abstract
We provide a systematic investigation of using physics-informed neural networks to compute Lyapunov functions. We encode Lyapunov conditions as a partial differential equation (PDE) and use this for training neural network Lyapunov functions. We analyze the analytical properties of the solutions to the Lyapunov and Zubov PDEs. In particular, we show that employing the Zubov equation in training neural Lyapunov functions can lead to approximate regions of attraction close to the true domain of attraction. We also examine approximation errors and the convergence of neural approximations to the unique solution of Zubov's equation. 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 region-of-attraction estimates in the large. Through a number of nonlinear examples, ranging from low to high dimensions, we demonstrate that the proposed framework can outperform traditional sums-of-squares (SOS) Lyapunov functions obtained using semidefinite programming (SDP).
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Optimization & Control

Died the same way β€” πŸ‘» Ghosted