Necessary and Sufficient Conditions for Template-Dependent Ordering of Path-Complete Lyapunov Methods

Debauche, Virginie; Rossa, Matteo Della; Jungers, Raphaël M.

doi:10.1145/3501710.3519539

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As reference benchmarks, we consider two switched linear systems in dimension 2 and 8 respectively, which are challenging as they are known to lead to poor approximation with classical techniques (see (Debauche, Della Rossa, and Jungers 2023, Section 5) and (Ahmadi et al 2014, Example 5.2)). The first one serves as proof of concept, while the second example shows that in higher dimensions, neural Lyapunov functions are competitive with SOS-based techniques both in terms of precision and (as suggested earlier in Figure 1) in computation time.…”

Section: Numerical Resultsmentioning

confidence: 99%

Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions

Debauche,

Edwards,

Jungers

et al. 2024

AAAI

View full text Add to dashboard Cite

Neural-based, data-driven analysis and control of dynamical systems have been recently investigated and have shown great promise, e.g. for safety verification or stability analysis. Indeed, not only do neural networks allow for an entirely model-free, data-driven approach, but also for handling arbitrary complex functions via their power of representation (as opposed to, e.g. algebraic optimization techniques that are restricted to polynomial functions). Whilst classical Lyapunov techniques allow to provide a formal and robust guarantee of stability of a switched dynamical system, very little is yet known about correctness guarantees for Neural Lyapunov functions, nor about their performance (amount of data needed for a certain accuracy). We formally introduce Neural Lyapunov functions for the stability analysis of switched linear systems: we benchmark them on this paradigmatic problem, which is notoriously difficult (and in general Turing-undecidable), but which admits existing recently-developed technologies and theoretical results. Inspired by switched systems theory, we provide theoretical guarantees on the representative power of neural networks, leveraging recent results from the ML community. We additionally experimentally display how Neural Lyapunov functions compete with state-of-the-art results and techniques, while admitting a wide range of improvement, both in theory and in practice. This study intends to improve our understanding of the opportunities and current limitations of neural-based data-driven analysis and control of complex dynamical systems.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions

Debauche,

Edwards,

Jungers

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…As reference benchmarks, we consider two switched linear systems in dimension 2 and 8 respectively, which are challenging as they are known to lead to poor approximation with classical techniques (see [15,Section 5] and [2,Example 5.2]). The first one serves as proof of concept, while the second example shows that in higher dimensions, neural Lyapunov functions are competitive with SOS-based techniques both in terms of precision and (as suggested earlier in Figure 1) in computation time.…”

Section: Numerical Resultsmentioning

confidence: 99%