Description:

The current success story of data science calls for interpretable machine learning methods. For instance, in the context of sampling, graph-based learning or neural networks, PDE-based methods have proven to be both efficient and apt for mathematical analysis.

This workshop brings together experts and young researchers in these two vibrant fields and aims to create a stimulating environment for exchanging scientific ideas and establishing new collaborations.

Keynote Speakers:

Eldad Haber (University of British Columbia, Canada)
Gitta Kutyniok (Ludwig-Maximilians-Universität München, Germany)
Michael Unser (EPFL, France)

Speakers:

• Matthias J Ehrhardt (University of Bath, UK)
• Tamara Grossmann (University of Cambridge, UK)
• Bamdad Hosseini (University of Washington, Seattle, USA)
• Arnulf Jentzen (University of Muenster, Germany)
• Anna Korba (ENSAE Paris, France)
• Yury Korolev (University of Cambridge, UK)
• Lisa Maria Kreusser (University of Bath, UK)
• Carlo Marcati (Università degli Studi di Pavia , Italy)
• Nikolas Nüsken (University of Potsdam, Germany)
• Josiah Park (Texas A&M University, USA)
• Phillipp Petersen (Universty of Vienna, Austria)
• Clarice Poon (Universty of Bath, UK)
• Tim Roith (Friedrich-Alexander Universität Erlangen-Nürnberg, Germany)
• Dejan Slepcev (Carnegie Mellon University, Pittsburgh, USA)
• Matthew Thorpe (University of Manchester, UK)
• Nicolas Garcia Trillos (University of Wisconsin, Madison, USA)
• Urbain Vaes (Inria Paris. France)
• Harini Veeraraghavan (Memorial Sloan Kettering Cancer Center, USA)
• Stephan Wojtowytsch (Texas A&M University, College Station, USA)
• Yunan Yang (ETH Zürich, Switzerland)