•   When: Wednesday, February 16, 2022 from 02:00 PM to 03:00 PM
•   Speakers: Fang-Yi Yu
•   Location: ZOOM only
•   Export to iCal

Abstract: 

In the age of artificial intelligence, properly deployed AI technology can transform society at every level, from individuals making decisions to institutes developing better policies. To achieve this, we need to understand the interaction between AI and society, such as how society provides AI inputs and how AI's outputs may affect society when strategic behavior is possible.
 
I will highlight two examples of my work about this interaction: 1) Information elicitation: How can we elicit and aggregate high-quality information from strategic agents? Using variational statistics, I design peer prediction mechanisms that reward strategic agents for truthful reports even without verification. 2) Performative prediction: Can standard learning algorithms converge in supervised learning when the outcome distribution (strategically) responds to our predictive models? With techniques in dynamical systems, I show that the learning algorithm can converge to the global stable and optimal point when the learning rate is small enough, but exhibits Li-Yorke chaos when the algorithm is not cautious in the learning rates or has an overwhelming influence on the data distribution.

 Bio:

Fang-Yi is currently a Postdoctoral fellow at Harvard School of Engineering and Applied Sciences.  He received the Ph.D. in Computer Science from the University of Michigan, and worked as a Postdoctoral research fellow at the School of Information at the University of Michigan.  His research is broadly situated at the interface between machine learning, artificial intelligence, and economics.  His recent work focuses on machine learning with strategic agents.