1 code implementation • NeurIPS 2021 • Federico López, Beatrice Pozzetti, Steve Trettel, Michael Strube, Anna Wienhard
We propose the use of the vector-valued distance to compute distances and extract geometric information from the manifold of symmetric positive definite matrices (SPD), and develop gyrovector calculus, constructing analogs of vector space operations in this curved space.
2 code implementations • 9 Jun 2021 • Federico López, Beatrice Pozzetti, Steve Trettel, Michael Strube, Anna Wienhard
We propose the systematic use of symmetric spaces in representation learning, a class encompassing many of the previously used embedding targets.
1 code implementation • 11 May 2021 • Federico López, Beatrice Pozzetti, Steve Trettel, Anna Wienhard
Learning faithful graph representations as sets of vertex embeddings has become a fundamental intermediary step in a wide range of machine learning applications.
no code implementations • 10 Dec 2020 • Daniel Spitz, Anna Wienhard
Persistent homology provides a robust methodology to infer topological structures from point cloud data.
Point Processes Probability
no code implementations • 15 Oct 2019 • Beatrice Pozzetti, Andrés Sambarino, Anna Wienhard
We study Anosov representations whose limit set has intermediate regularity, namely is a Lipschitz submanifold of a flag manifold.
Differential Geometry Dynamical Systems Group Theory