ECE Seminar: Elinor Ginzburg-Ganz

ECE Seminar: Elinor Ginzburg-Ganz

Title: "On the Tension Between Data-Driven and Classical Optimal Control Approaches

Abstract: As control theory enters a new, data-driven era, a fundamental tension with classical optimal control emerges. This talk presents a new theory to address fundamental problems that arise when combining machine learning or reinforcement learning algorithms in the optimal control of complex, uncertain systems. Specifically, we will target the problem of redundant information in machine learning estimators. By utilizing unique properties of the Pontryagin's Minimum Principle, we identify the minimal information required to make an optimal decision. These results help illuminate the limits of existing controllers operating under high uncertainty, and can aid in the design of more computationally efficient machine learning estimators for this task.

Bio: Elinor Ginzburg-Ganz received her BSc from the Faculty of Electrical and Computer Engineering at the Technion in 2023. She is currently pursuing her PhD on a direct track in the Faculty of Electrical and Computer Engineering, also at the Technion. Her research interests include energy and power systems, system theory & optimal control, and machine learning. Ms. Ginzburg Ganz was the recipient of The Vatat Student Research Award in the Field of Data-Sciences in 2024, and The Freud Award for Excellence in Research in 2025.