This HIM School is a week-long event directed at PhD students and recent Postdocs, which will take place within the framework of the Dual Trimester Program "Geometric Statistics: theory, application, and computation".
Everyone interested in participating - regardless of whether financial support is needed - must apply, except for:
- PhD students and early-career researchers, who were already invited and have confirmed to be at HIM during the period of this School. (They are automatically admitted to this event.)
- Researchers from the HCM, in particular, early-career researchers, who may join upon request to the program coordinators Emma Seggewiss and Kanami Ueda. (You can find the email addresses below.)
Everyone will be notified in due time about whether participation and partial financial support is possible. After being selected as participant, you will be invited to register.
Everyone will be notified in due time about whether participation and partial financial support is possible. After being selected as participant, you will be invited to register.
Lecture series by:
- Fernando Galaz-Garcia (Durham University, UK)
- Elton Hsu (Northwestern University, Evanston, US)
- Xavier Pennec (INRIA, Université Côte d’Azur, FR)
- Amy Willis (University of Washington, US)
Description:
Geometric statistics focuses on statistical methods that recognize and exploit the geometric structure of data sets, data objects, and parameters. Its importance arises from an increasing amount of modern data naturally living on curved, constrained, or stratified spaces rather than flat Euclidean spaces. Notable examples of these data objects include shapes, networks, covariance matrices, trees, or configuration spaces. On such objects or spaces parametrizing them, traditional statistical methods may fail or not apply. New mathematics to deal with these issues often yield surprising results and high relevance for complex applications in fields such as structural biology, physical chemistry, medical imaging, robotics, and forensics.
The Introductory School will provide a set of foundational mini courses designed to equip participants, especially young researchers and newcomers, with an overview of pertinent background in geometry, topology, probability, statistics, and computation specific to statistics and data analysis in settings that are non-Euclidean. In particular, mini courses will cover foundations of geometric statistics, asymptotics of Fréchet means on manifolds and stratified spaces, SDEs on manifolds, and Alexandrov and RCD spaces. Together, these mini courses aim to establish a shared scientific language for participants entering the broader program in geometric statistics.