Date: April 27, 2026
Time: 3:45-5 p.m.
Location: Gates Hall, 122 or Click here to attend via Zoom
Speaker: Ira Globus-Harris, assistant research professor, Cornell's Center for Enterprise for Data and Society, Cornell Tech
Abstract: Designing effective collaboration between humans and AI systems is crucial for leveraging their complementary abilities in complex decision tasks. But how should agents possessing unique knowledge—like a human expert and an AI model—interact to reach decisions better than either could alone?
In this talk, I will introduce a collection of tools based in machine learning theory and algorithmic game theory which allow us to develop efficient "collaboration protocols", where parties iteratively exchange only low-dimensional information—their current predictions or best-response actions—without needing to share underlying features and which guarantee that the agents' final predictions are provably competitive with an optimal predictor with access to their joint features. Together, these results offer a new foundation for building systems that achieve the power of pooled knowledge through tractable interaction alone.
Bio: Ira Globus-Harris is an assistant research professor at Cornell's Center for Enterprise for Data and Society, where they are hosted by danah boyd and Nikhil Garg. They received their PhD from the University of Pennsylvania, where they worked with Aaron Roth and Michael Kearns on machine learning theory and responsible computing.