Conference Goal

In recent years, the field of Machine Learning has made significant progress in theory and applications. This success is rooted in the mutual stimulation of mathematical insight and experimental studies. On the one hand, mathematics allows to conceptualize and formalize core problems within learning theory, leading, for instance, to performance bounds for learning algorithms. On the other hand, experimental studies confirm theoretical predictions and instigate new directions in theoretical research. This meeting aims to discuss the interaction between theory and practice, with focus on the current gaps between the two. The talks will be centered around themes including the following.

• Gradient Methods (gradient optimization, stochastic gradient, natural gradients, gradient applied to deep networks, ...),
• Natural Geometric Structures (Information Geometry, optimal transport geometry, ...),
• Generalisation Theory (statistical learning theory, complexity measures, Ill-posed inverse problems, regularization, implicit bias...)
• Functional analytical tools (approximation theory, harmonic analysis, ...)
• Overparametrization and random matrix theory (neural tangent kernel, lazy training, convergence of gradient descent, generalization bounds, ...)

Confirmed Keynote Speakers

• Francis Bach   Centre de Recherche INRIA de Paris, France
• Misha Belkin   University of California San Diego, USA
• Stefanie Jegelka  Massachusetts Institute of Technology, USA and Technical University of Munich, Germany
• Markos Katsoulakis   University of Massachusetts Amherst, USA
• Gitta Kutyniok   Ludwig-Maximilians-Universität München, Germany
• Sayan Mukherjee   Leipzig University, Germany
• Grant M. Rotskoff   Stanford University, USA
• Gabriele Steidl   TU Berlin, Germany
• Matus Telgarsky  New York Univesity, USA

Organisers

• Nihat Ay   Hamburg University of Technology, Germany and Santa Fe Institute, USA
• Martin Burger   DESY and University of Hamburg, Germany
• Benjamin Gess   TU Berlin and Max Planck Institute for Mathematics in the Sciences, Germany
• Guido Montúfar   University of California, Los Angeles, USA and Max Planck Institute for Mathematics in the Sciences, Germany

Scientific Committee

• Alexandra Carpentier  University of Potsdam, Germany
• Asja Fischer  Ruhr University Bochum, Germany
• Armin Iske  University of Hamburg, Germany
• Stefanie Jegelka  Massachusetts Institute of Technology, USA and Technical University of Munich, Germany
• Parvaneh Joharinad  Leipzig University and Max Planck Institute for Mathematics in the Sciences, Germany
• Sören Laue  University of Hamburg, Germany
• Johannes Lederer  University of Hamburg, Germany
• Marco Mondelli  Institute of Science and Technology, Austria
• Sayan Mukherjee  Leipzig University, Germany
• Liza (Elizaveta) Rebrova  Princeton University, USA
• Gabriele Steidl  TU Berlin, Germany
• Diaaeldin Taha  Max Planck Institute for Mathematics in the Sciences, Germany
• Melanie Weber  Harvard University, USA
• Jens-Peter M. Zemke  Hamburg University of Technology, Germany

Conference Program

For the detailed list of conference program, talks and posters, please visit here.

Application for Participation and Presentation

If you would like to participate in the conference, you are kindly invited to apply here, where you can also submit a title and an abstract (up to 2 pages, pdf) in case you would like to contribute a talk or/and a poster. The application deadline is May 1^st, 2025. A notification email about the outcome of your application will be sent out in early June, 2025. The registration fee for accepted participants is 60 Euros.

We have a limited number of travel grants for student participants. If you are interested in applying for travel support please indicate this in your application statement and provide contact information of a reference person.

For registration and submission issues, contact Hojat Naghavi: dsf-it@tuhh.de

Administrative Contact

Imke Christiane Bartscher and Daniela Gascon Bosqued: dsf-conference@tuhh.de