Consensus in Asynchronous Multiagent Systems. III. Constructive Stability and Stabilizability

Kozyakin, Victor; Kuznetsov, N. A.; Chebotarev, Pavel

doi:10.1134/s0005117919060018

Cited by 4 publications

(2 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, the JSR does not share the same nice algebraic properties as the spectral radius and is extremely hard to compute in practice. Indeed, approximating the JSR is NP-hard (Blondel and Tsitsiklis 1997), whereas deciding whether the JSR is smaller than one or not is Turingindecidable (Blondel and Canterini 2008), and there does not exist any algebraic criterion to decide the stability (nonalgebraicity) of switched systems (Kozyakin 1990). Despite these theoretical limitations, the approximation of the JSR has been tackled by many researchers.…”

Section: Approximation Of the Jsrmentioning

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: Approximation Of the Jsrmentioning

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

“…Unfortunately, the JSR does not share the same nice algebraic properties as the spectral radius and is extremely hard to compute in practice. Indeed, approximating the JSR is NP-hard [11], whereas deciding whether the JSR is smaller than one or not is Turing-indecidable [8], and there does not exist any algebraic criterion to decide the stability (non-algebraicity) of switched systems [23]. Despite these theoretical limitations, the approximation of the JSR has been tackled by many researchers.…”

Section: Approximation Of the Jsrmentioning

confidence: 99%