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. Design of expressive and stable graph machine learning architectures.

Geometric Deep Learning

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

Optimization on Manifolds

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

Geometry & AI4Science

Geometric methods for resource-efficient and interpretable scientific machine learning.

Geometry of Foundation Models

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