16th Annual Karl Menger Lecture and Celebration: “Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI” by Xunyu Zhou

The Department of Applied Mathematics at Illinois Tech is proud to host the 16th annual Remembering Karl Menger Celebration April 13–14, 2026, at the university’s Mies Campus in Chicago.

Featured lecturer Xunyu Zhou, the Liu Family Professor of Financial Engineering and director of the Nie Center for Intelligent Asset Management at Columbia University, will speak beginning at 6 p.m. on Monday, April 13. Zhou’s current research focuses on developing a foundational theory for continuous-time reinforcement learning and its applications to financial decision-making. Previously, he worked on quantitative behavioral finance, time inconsistency, and stochastic control. Zhou is a fellow of IEEE and SIAM. He previously was the Nomura Professor of Mathematical Finance at the University of Oxford from 2007 to 2016.

Please RSVP here: https://forms.office.com/r/6LWLggkGWC

For more information, please contact Department Coordinator Faith Kancauski and/or Associate Teaching Professor Despina Stasi.

Lecture Title:

Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI

Abstract: 

In this lecture I will discuss the key connections and differences between the model-based and model-free paradigms from the perspectives of reinforcement learning and generative AI. I will argue that establishing a sufficiently accurate model is both impossible and unnecessary for the ultimate purpose of making optimal decisions, but there is some quantity, one that is an aggregate measure of the model parameters and control actions,  that needs to be learned and can indeed be learned efficiently in a data-driven way.