Neural Continuous-Time Supermartingale Certificates

Journal Article (2025)
Author(s)

Grigory Neustroev (TU Delft - Algorithmics)

Mirco Giacobbe (University of Birmingham)

Anna Lukina (TU Delft - Algorithmics)

Research Group
Algorithmics
DOI related publication
https://doi.org/10.1609/aaai.v39i26.34966
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Algorithmics
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Issue number
26
Volume number
39
Pages (from-to)
27538-27546
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

We introduce for the first time a neural-certificate framework for continuous-time stochastic dynamical systems. Autonomous learning systems in the physical world demand continuous-time reasoning, yet existing learnable certificates for probabilistic verification assume discretization of the time continuum. Inspired by the success of training neural Lyapunov certificates for deterministic continuous-time systems and neural supermartingale certificates for stochastic discrete-time systems, we propose a framework that bridges the gap between continuous-time and probabilistic neural certification for dynamical systems under complex requirements. Our method combines machine learning and symbolic reasoning to produce formally certified bounds on the probabilities that a nonlinear system satisfies specifications of reachability, avoidance, and persistence. We present both the theoretical justification and the algorithmic implementation of our framework and showcase its efficacy on popular benchmarks.

Files

34966-Article_Text-39033-1-2-2... (pdf)
(pdf | 0.376 Mb)
- Embargo expired in 11-10-2025
License info not available