The Geometric Machine Learning Group at Harvard University studies how to identify geometry structure in data and models and how to leverage such structure for the design of efficient machine learning algorithms with provable guarantees. We also work on applications of Geometric Machine Learning in the Sciences.
To learn more about our research, this AI Magazine article surveys Geometric Machine Learning, including our work within this area.
We are affiliated with the Harvard Data Science Initiative and the Kempner Institute. We are also part of the NSF AI Institute in Dynamic Systems.
Our research is supported in part by the National Science Foundation (DMS-2406905 and CBET-2112085), a Sloan Research Fellowship, the Harvard Data Science Initiative, and the Harvard Dean’s Fund for Promising Scholarship.