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 and geometry and learning data representations in suitable non-Euclidean spaces. Non-Euclidean geometry of foundation models.

Graph Machine Learning

Leveraging geometric structure for efficient learning on graphs. Design of expressive and stable graph machine learning architectures.

Learning Under Symmetry

Designing geometric architectures. Understanding learning-theoretic trade-offs in geometric settings.

Geometry & AI4Science

Leverage geometric machine learning for resource-efficient and interpretable scientific machine learning.

Optimization on Manifolds

Exploiting geometric structure in (non)convex (constrained) optimization.

Geometry of Foundation Models

Leveraging data and model geometry for more efficient and transparent foundation models.