Necmiye Ozay
University of Michigan
Seminar Information
Data-driven and learning-based methods have attracted considerable attention in recent years both for the analysis of dynamical systems and for control design. While there are many interesting and exciting results in this direction, our understanding of fundamental limitations of learning for control is lagging. This talk will focus on the question of when learning can be hard or impossible in the context of dynamical systems and control. In the first part of the talk, I will discuss a new observation on immersions and how it reveals some potential limitations in learning Koopman embeddings. In the second part of the talk, I will show what makes it hard to learn to stabilize linear systems from a sample-complexity perspective. While these results might seem negative, I will conclude the talk with some thoughts on how they can inspire interesting future directions.
Necmiye Ozay received her B.S. in Electrical and Electronics Engineering from Bogazici University in 2004, her M.S. in Electrical Engineering from Pennsylvania State University in 2006, and her Ph.D. in Electrical Engineering from Northeastern University in 2010. Between 2010 and 2013, she was a Control and Dynamical Systems postdoctoral scholar at Caltech. In 2013, she joined the University of Michigan faculty, where she is currently a Professor of Electrical Engineering and Computer Science and of Robotics. Her research interests include dynamical systems, control, optimization and formal methods, with applications in cyber-physical systems, system identification, verification and validation, safe autonomy and safe AI. She received a DARPA Young Faculty Award, an NSF CAREER Award, a NASA Early Career Faculty Award, a DARPA Director’s Fellowship, an ONR Young Investigator Award, and 2021 Antonio Ruberti Young Researcher Prize from the IEEE Control Systems Society. She served as a program co-chair for the 22nd ACM Conference on Hybrid Systems: Computation and Control (HSCC) in 2019, a program co-chair for the IFAC Conference on Analysis and Design of Hybrid Systems (ADHS) in 2021, a program co-chair for International Conference on Cyber-Physical Systems (ICCPS) in 2024, and the general chair for 2025 Annual Conference on Learning for Dynamics and Control (L4DC). She is an IEEE Fellow and an associate editor of Automatica and Discrete Event Dynamic Systems.