IST Lunch Bunch
Yanan Sui is an assistant professor at Tsinghua University. Yanan got his Bachelor's degree from Tsinghua University and PhD from Caltech in Computation & Neural Systems. He worked as a postdoc with Profs. Joel Burdick and Yisong Yue at Caltech CMS and with Prof. Fei-Fei Li at Stanford CS before joining Tsinghua. His research interests are machine learning, neural engineering, and robotics. He is currently working on the theory and algorithms for online learning with human in the loop and applications on neural rehabilitation and robotics.
Bandit algorithms tackle the fundamental challenge of balancing exploration (collecting data for learning better models) and exploitation (using the estimates to make decisions). In this talk, I will formalize bandit problems with preference feedback, with structured decision spaces, and with safety constraints (when bad samples are not allowed). These constraints commonly exist in many applications. In particular, we are motivated by online decision-making for clinical treatment and robotic control. This talk will exhibit several algorithms for these constrained optimization problems. Theoretical guarantees and empirical efficiencies of our algorithms will be presented. I will also show our clinical practices of online decision-making for neuromodulation.