This workshop is directed at the participants in the Dual Trimester Program "Geometric Statistics: theory, application, and computation". It is not possible to apply only for this workshop.
Researchers from the HCM, in particular, early-career researchers, are welcome upon request.
Organizers:
- Shreya Arya (University of Pennsylvania)
- Karen Habermann (University of Warwick)
- Stephan Huckemann (University of Göttingen)
- Ezra Miller (Duke University)
- Yvo Pokern (University College London)
- Wilderich Tuschmann (Karlsruhe Institute of Technology)
- Zhigang Yao (National University of Singapore)
Description:
An increasing amount of modern data naturally lives on curved, constrained, or stratified spaces, including spaces with singularities. Classical statistical methodology often falls short when faced with curvature effects, non‑smooth structure, or singular behaviour. Deepening our understanding of stochastic processes on both smooth and singular spaces and adapting statistical methodology for such processes are therefore paramount for capturing modern data’s geometric variability and for advancing the theoretical foundations of geometric statistics.
This workshop aims to bring together researchers working at the interface of stochastic analysis, geometric statistics, and computation on manifolds and singular spaces. The central focus of the workshop is the study of stochastic processes on manifolds and, crucially, on singular spaces, where standard techniques and standard statistical methodology may break down yet many real‑world datasets naturally live in. By improving our understanding of stochastic processes and statistical models in these settings, we aim to enable more robust statistical methods capable of handling complex geometric variability. Such developments will drive progress in geometric statistics, with applications in shape analysis, computational anatomy, topological data analysis, and machine learning on structured domains.