Learning to Decide Under Uncertainty: From Bandit Theory to Health Applications by Prof. Mengyan Zhang

Abstract
How can AI systems make reliable sequential decisions in dynamic environments with noisy, aggregated, or partial feedback? This challenge motivates research on sequential decision-making frameworks such as multi-armed bandits, reinforcement learning, and active learning.

In this talk, I will review my work on bandit theory under realistic data constraints, including aggregated and multi-precision feedback, and present application-driven sequential decision tasks in scientific discovery, public health, and recommender systems. I will conclude by outlining open challenges and future research directions at the intersection of theory and real-world applications.

About the Speaker
Dr. Mengyan Zhang is an Assistant Professor in the School of Computer Science at the University of Bristol. She is also a visiting researcher at the University of Oxford and a member of the Machine Learning and Global Health Network. Prior to joining Bristol, she was a postdoctoral researcher at the University of Oxford. She received her PhD from the Australian National University and was affiliated with Data61, CSIRO. Her research focuses on sequential decision making in machine learning, including multi-armed bandits, reinforcement learning and active learning, with applications in areas such as disease surveillance, synthetic biology, and public policy.