aiqbench analysis
This research introduces a scalable verification method that provides formal error bounds for neural network approximations of nonlinear dynamical systems, enabling their safe use as surrogates in safety-critical control applications. By treating approximation errors as bounded disturbances, the approach significantly outperforms existing benchmarks and extends applicability to previously intractable tasks like neural network compression and Koopman operator training. The work bridges the gap between data-driven modeling and rigorous systems control, offering a practical pathway for deploying neural networks in high-stakes environments.
Certified Neural Approximations of Nonlinear Dynamics
arXiv:2505.15497v3 Announce Type: replace Abstract: Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such systems. However, in safety-critical contexts, the use of neural approximations requires formal bounds on their closeness to the underlying system. To address this fundamental challenge, we propose a novel, adaptive, and parallelizable verification method based on certified first-order models. Our approach provides formal error bounds on the neural approximations of dynamical systems, allowing them to be safely employed as surrogates by interpreting the error bound as bounded disturbances acting on the approximated dynamics. We demonstrate the effectiveness and scalability of our method on a range of established benchmarks from the literature, showing that it significantly outperforms the state of the art. Furthermore, we show that our framework can successfully address additional scenarios previously intractable for existing methods -- neural network compression and an autoencoder-based deep learning architecture for training Koopman operators for the purpose of trajectory prediction.
Abstract:Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such systems. However, in safety-critical contexts, the use of neural approximations requires formal bounds on their closeness to the underlying system. To address this fundamental challenge, we propose a novel, adaptive, and parallelizable verification method based on certified first-order models. Our approach provides formal error bounds on the neural approximations of dynamical systems, allowing them to be safely employed as surrogates by interpreting the error bound as bounded disturbances acting on the approximated dynamics. We demonstrate the effectiveness and scalability of our method on a range of established benchmarks from the literature, showing that it significantly outperforms the state of the art. Furthermore, we show that our framework can successfully address additional scenarios previously intractable for existing methods -- neural network compression and an autoencoder-based deep learning architecture for training Koopman operators for the purpose of trajectory prediction.
Machine Learning (cs.LG); Systems and Control (eess.SY)
arXiv:2505.15497 [cs.LG]
(or arXiv:2505.15497v3 [cs.LG] for this version)
Full text under the publisher's open licence · 177 words
Related coverage
Data-driven Koopman mode approximation: A neural power iteration algorithm
arXiv · Aug 28, 2026
Learning Lyapunov Operators for Nonlinear Systems
arXiv · Sep 17, 2026
Neural ARFIMA model for forecasting BRIC exchange rates with long memory
arXiv · Jun 15, 2026
Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecasting
arXiv · Aug 6, 2026