Verifying Nonlinear Neural Feedback Systems using Polyhedral Enclosures

Samuel I. Akinwande, Chelsea Rose Sidrane, Mykel Kochenderfer, Clark Barrett
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:737-760, 2026.

Abstract

As dynamical systems controlled by neural networks become increasingly prevalent, it is critical to ensure their safe operation. Although efficient techniques exist to handle neural systems with linear transition functions, few scalable methods address the nonlinear case. We propose a novel algorithm for verifying nonlinear neural feedback systems using forward reachability analysis. Our algorithm leverages the structure of the nonlinear transition functions to compute tight linear abstractions which we call polyhedral enclosures. These are then encoded as mixed-integer linear programs (MILPs) and solved to yield a sound over-approximation of the forward-reachable set. We evaluate our algorithm on representative benchmarks and demonstrate an order of magnitude improvement over the previous state of the art

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-akinwande26a, title = {Verifying Nonlinear Neural Feedback Systems using Polyhedral Enclosures}, author = {Akinwande, Samuel I. and Sidrane, Chelsea Rose and Kochenderfer, Mykel and Barrett, Clark}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {737--760}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/akinwande26a/akinwande26a.pdf}, url = {https://proceedings.mlr.press/v331/akinwande26a.html}, abstract = {As dynamical systems controlled by neural networks become increasingly prevalent, it is critical to ensure their safe operation. Although efficient techniques exist to handle neural systems with linear transition functions, few scalable methods address the nonlinear case. We propose a novel algorithm for verifying nonlinear neural feedback systems using forward reachability analysis. Our algorithm leverages the structure of the nonlinear transition functions to compute tight linear abstractions which we call polyhedral enclosures. These are then encoded as mixed-integer linear programs (MILPs) and solved to yield a sound over-approximation of the forward-reachable set. We evaluate our algorithm on representative benchmarks and demonstrate an order of magnitude improvement over the previous state of the art} }
Endnote
%0 Conference Paper %T Verifying Nonlinear Neural Feedback Systems using Polyhedral Enclosures %A Samuel I. Akinwande %A Chelsea Rose Sidrane %A Mykel Kochenderfer %A Clark Barrett %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-akinwande26a %I PMLR %P 737--760 %U https://proceedings.mlr.press/v331/akinwande26a.html %V 331 %X As dynamical systems controlled by neural networks become increasingly prevalent, it is critical to ensure their safe operation. Although efficient techniques exist to handle neural systems with linear transition functions, few scalable methods address the nonlinear case. We propose a novel algorithm for verifying nonlinear neural feedback systems using forward reachability analysis. Our algorithm leverages the structure of the nonlinear transition functions to compute tight linear abstractions which we call polyhedral enclosures. These are then encoded as mixed-integer linear programs (MILPs) and solved to yield a sound over-approximation of the forward-reachable set. We evaluate our algorithm on representative benchmarks and demonstrate an order of magnitude improvement over the previous state of the art
APA
Akinwande, S.I., Sidrane, C.R., Kochenderfer, M. & Barrett, C.. (2026). Verifying Nonlinear Neural Feedback Systems using Polyhedral Enclosures. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:737-760 Available from https://proceedings.mlr.press/v331/akinwande26a.html.

Related Material