11–13 July 2022, Heidelberg University and Heidelberg Institute for Theoretical Studies
In recent years, there has been a remarkable increase in research into applying Geometry to Machine Learning problems epitomized by the upward trend of Geometric Deep Learning architectures, tools, and publications. Geometry has successfully provided diverse methods for describing the structure of data, and researchers have suggested frameworks for analyzing, unifying, and generalizing Machine Learning techniques to new settings.
This three-day workshop will bring together researchers and practitioners of Geometry and Machine Learning to interact and exchange ideas. The workshop will consist of invited talks, including three keynotes by well-known experts. There will be two hands-on mini-courses on implementing geometric deep learning methods in Python.
- Erik Bekkers (Amsterdam) [homepage][Twitter]
- Nicolas Guigui (CNRS) [LinkedIn]
- Pim de Haan (Amsterdam) [homepage][Twitter]
- Anastasis Kratsios (McMaster) [homepage][LinkedIn]
- Maxim Kochurov (PyMC Labs) [homepage][Twitter]
- Maximilian Nickel (Facebook AI) [homepage]
- Björn Ommer (Munich) [homepage]
- Xavier Pennec (INRIA) [homepage]
- Beatrice Pozzetti (Heidelberg) [homepage]
- Emanuele Rodolà (Sapienza University) [homepage]
Participation is free.
If you wish to attend, please register by June 26th, 2022. Registration for in-person participation is now closed. Registration for remote participation is open until Jul 6th, 2022. Registration for remote participation is now closed.
If you have any questions, feel free to contact the organizers via email.
Valentina Disarlo, Diaaeldin Taha, Anna Wienhard