July 26 - 30, 2021

Lipschitz-Saal (Endenicher Allee 60, Bonn)

Organizers: Sven Otto (Universität Bonn), Michael Vogt (Universität Ulm)

Update: This event is planned as hybrid. Due to the current situation, we can currently only guarantee online participation. If the pandemic situation allows it, a limited number of people can also participate on-site. Please indicate in the application form whether you prefer online or in-person participation. The deadline for applications is April 30, 2021. All applicants will be notified by May 10. Invitations will initially be sent out for online participation only. A decision on possible additional on-site participation will be made at a later date

Description:

Many estimation problems in modern statistics are high-dimensional, that is, the number of parameters to be estimated is much higher than the number of available observations. High-dimensional estimation problems have received a lot of attention in recent years and a wide range of statistical tools have been developed to deal with them. Prominent examples are the Lasso, boosting algorithms, neural networks and their recent reincarnation in deep learning.

The Hausdorff School, which is directed at graduate students and postdocs, will give insight into recent advances in the field of high-dimensional statistics. The courses will cover topics such as theory for high-dimensional linear models, bootstrap methods in high dimensions, neural networks and functional data analysis.

Key Speakers: 

The following speakers will give a lecture series:

•  Kengo Kato (Cornell University, US)
• Hannes Leeb (University of Vienna, Austria)
• Johannes Schmidt-Hieber (University of Twente, Netherlands)
• Jane-Ling Wang (University of California, Davis, US)