The Exponential Turnpike Property for Neural Differential Equations

Gugat M (2025)

Publication Type: Conference contribution

Publication year: 2025

Pages Range: 142-147

Conference Proceedings Title: 2025 29th International Conference on Methods and Models in Automation and Robotics (MMAR)

Event location: Miedzyzdroje PL

Journal Issue: 2025

DOI: 10.1109/MMAR65820.2025.11151091

Abstract

We consider an optimal control problem where the tracking term in the objective function is related to a weighted H1-norm. To be specific, we study a system that is governed by a neural ordinary differential equation that is related to machine learning. We show that a simultaneous exact controllability property of the system implies an exponential turnpike property for the state. Moreover, we show that also the simultaneous exponential stabilizability of the system yields an exponential turnpike property.

Authors with CRIS profile

Martin Gugat Lehrstuhl für Dynamics, Control, Machine Learning and Numerics (Alexander von Humboldt-Professur)

How to cite

APA:

Gugat, M. (2025). The Exponential Turnpike Property for Neural Differential Equations. In 2025 29th International Conference on Methods and Models in Automation and Robotics (MMAR) (pp. 142-147). Miedzyzdroje, PL.

MLA:

Gugat, Martin. "The Exponential Turnpike Property for Neural Differential Equations." Proceedings of the 29th International Conference on Methods and Models in Automation and Robotics (MMAR), Miedzyzdroje 2025. 142-147.

BibTeX: Download