Received an EPSRC Pathway Postdoctoral Fellowship.
Keyan Miao
I'm currently a DPhil candidate in the Department of Engineering Science at University of Oxford , as a member of the Control Engineering Group, under the supervision of Prof. Antonis Papachristodoulou and Dr. Konstantinos Gatsis.
Prior to joining the DPhil program, I obtained my master's degree in Control Systems from Imperial College London , under the supervision of Professor Richard Vinter and a BEng in Detection, Guidance and Control at Northwestern Polytechnical University. Outside academia, I play violin with the Hertford College Orchestra.
Building reliable learning systems through control-theoretic insight.
News
MoreAttended the 14th International Conference on Learning Representations (ICLR) in Rio de Janeiro, Brazil.
I successfully defended my DPhil thesis!
Gave a talk on Efficient and Reliable AI at ETH AI Center Fellowship Symposium.
Paper Learning Koopman Representations with Controllability Guarantees accepted by 14th International Conference on Learning Representations (ICLR).
Paper Data-Enabled Predictive Control for Nonlinear Systems Based on a Koopman Bilinear Realization accepted by 2025 IEEE 64th Conference on Decision and Control.
Research
More
01 Learning With Constraints/Guarantees
Building constraints, structure, and formal guarantees directly into learning.
02 Control-Informed Machine Learning
Using control perspectives to understand and improve learning models, training, and optimization.
03 Learning-Based Control
Integrating learning with modeling, estimation, prediction, and control of dynamical systems.
Publications from Google Scholar
All publications
Designing neural controllers with optimality and stability guarantees by learning input-output dissipativity
Automatica 191, 113120, 2026
Learning Koopman Representations with Controllability Guarantees
The Fourteenth International Conference on Learning Representations, 2026
Scholar Published
Data-enabled predictive control for nonlinear systems based on a Koopman bilinear realization
2025 IEEE 64th Conference on Decision and Control (CDC), 6498-6503, 2025
Scholar Published
NLBAC: A neural ODE-based algorithm for state-wise stable and safe reinforcement learning
Neurocomputing, Volume 638, Article 130041, 2025
Opt-ODENet: Neural ODE controller design with differentiable optimization layers for safety and stability
Proceedings of the 7th Annual Learning for Dynamics and Control Conference, PMLR 283:1217–1229, 2025