I’m a doctoral researcher at Helmholtz Munich and at TUM under the supervision of Bastian Rieck and Fabian Theis. I am a member of AIDOS Lab researching topological and geometric machine learning and Theis Lab researching machine learning in single cell omics. My PhD is also part of the Munich School for Data Science (MUDS) graduate school.
My main research goal is to use topological machine learning and geometric statistics to study complex structures in data. In particular, I am keen to develop robust computational methods to analyse biological and single cell data across multiple scales of distances. At the same time, my work aims to advance our understanding of the mathematical foundations of deep learning using geometry and topology. I am especially interested in applications of the magnitude of metric spaces to machine learning.
🍩 Geometric and Topological Machine Learning
:mag: Metric Space Magnitude
:dna: Computational Biology
K. Limbeck, R. Andreeva, R. Sarkar, and B. Rieck: Metric Space Magnitude for Evaluating the Diversity of Latent Representations, Advances in Neural Information Processing Systems, 2024 (in press)
K. Limbeck, and B. Rieck: Detecting Spatial Dependence in Transcriptomics Data using Vectorised Persistence Diagrams, preprint, 2024
R. Andreeva, K. Limbeck, B. Rieck‡, and R. Sarkar‡: Metric Space Magnitude and Generalisation in Neural Networks, Accepted at TAG in Machine Learning at ICML, 2023
:computer: GitHub
:page_facing_up: Google Scholar
:blue_book: LinkedIn
:email: katharina [dot] limbeck [at] helmholtz-munich [dot] de