
Geometric Machine Learning
We study geometric structure in data and models and how to leverage such information
for the design of efficient machine learning algorithms with provable guarantees.
Our Research

Geometric Representation Learning
Characterizing data geometry and learning data representations in suitable non-Euclidean spaces.

Graph Machine Learning
Leveraging geometric structure for efficient learning on graphs.

Learning Under Symmetry
Designing geometric architectures. Understanding learning-theoretic trade-offs in geometric settings.
Latest News
- [04/2025] Papers at ICLR and ICLR Re-Align WorkshopA paper led by Zak Shumaylov and Peter Zaika (both at the University of Cambridge, UK) will be presented at ICLR…
- [04/2025] Andrew passes Qualifying ExamCongratulations, Andrew!…
- [03/2025] Aramont Fellowship for Emerging Science ResearchWe received a grant from the Aramont Foundation, which will support our research on geometry-informed models for scientific machine learning. Thank…
- [10/2024] Two Spotlights at NeurIPS 2024 and OPT 2024 paperTwo of our papers got accepted at NeurIPS as spotlights. Congrats to Bobak, Jason, and Lukas! B Kiani, J Wang, M Weber: Hardness of…
- [06/2024] Lukas receives Kempner FellowshipLukas was selected for a Kempner Institute Graduate Fellowship. Congratulations!…