Learning Lyapunov Operators for Nonlinear Systems
This research provides a theoretical foundation and a practical method for approximating Lyapunov functions, which are crucial for stability analysis in control theory and robotics.
This paper introduces a method for constructing Lyapunov functions for nonlinear dynamical systems using Fourier Neural Operators (FNOs).
The research establishes that a Lyapunov solution operator can be approximated by a trained neural network, which can then be used to find Lyapunov functions for a family of systems.
Numerical experiments show this approach can accurately approximate Lyapunov functions across different parameterized dynamics.
Constructing Lyapunov functions for nonlinear dynamical systems is a central problem in stability analysis, yet remains challenging. Lyapunov functions are commonly characterized as solutions to first-order partial differential equations (PDEs), but these solutions are typically obtained for single systems, limiting their reuse across systems. In this paper, we study the Lyapunov solution operator that maps a vector field to the corresponding Lyapunov function defined by a dissipation-based Lyapunov PDE. We establish that, on compact subsets of the domain of attraction and under exponential stability assumptions, this operator is well-defined, unique, and continuous with respect to perturbations of both the vector field and the dissipation function. These results provide a theoretical foundation for approximating Lyapunov functions uniformly over families of nonlinear systems. Building on these theoretical foundations, we employ Fourier Neural Operators (FNOs) as a data-driven approximation of the Lyapunov solution operator. Numerical experiments demonstrate that a single trained operator can accurately approximate the numerical Lyapunov functions across parameterized families of dynamics. This illustrates the potential of neural operators for approximating Lyapunov functions.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Lyapunov, neural networks, FNOs.
Source attribution: curated from arXiv cs.LG (@Amartya Mukherjee, Maxwell Fitzsimmons, David C. Del Rey Fernández, Jun Liu).