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

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

Exploiting geometric and topological structure in Graph Machine Learning.

Optimization and Machine Learning algorithms on geometric domains.

[02/2024] Melanie selected as Sloan Fellow
Melanie was selected as a 2024 Alfred P. Sloan Fellow in Mathematics. See the Press Release here….
[01/2024] Two Papers accepted at ICRL
“On the Hardness of Learning under Symmetries” (selected as spotlight) and “Effective Structural Encodings via Local Curvature Profiles” were accepted at…
[09/2023] New Group members
Bobak joined as the group’s first postdoc in July, Katya and Andrew joined as the group’s first PhD students. Welcome!…
[08/2023] Harvard Data Science Initiative Grant
We received a grant from the Harvard Data Science Initiative’s Competitive Research Fund to support our research on learning under symmetry….
[06/2023] Melanie was awarded the 2023 IMA Leslie Fox Prize.
Melanie was awarded the 2023 IMA Leslie Fox Prize in Numerical Analysis. See the Press Release here….