Speakers
Semi-plenary speakers
- Schönlieb, Carola-Bibiane - University of Cambridge, UK
- Tropp, Joel - California Institute of Technology, USA
Invited speakers
- Alaifari, Rima - ETH Zürich, Switzerland
- Belkin, Mikhail - University of California San Diego, USA
- Boedihardjo, March - ETH Zurich, Switzerland
- Boelcskei, Helmut - ETH Zürich, Switzerland
- Boyer, Claire - Sorbonne Université, France
- Bronstein, Michael - Imperial College London, UK
- Cayci, Semih - RWTH Aachen University, Germany
- Cohen, Nadav - Tel Aviv University, Israel
- Dirksen, Sjoerd - Utrecht University, The Netherlands
- Fornasier, Massimo - TU Munich, Germany
- Foucart, Simon - Texas A&M University, USA
- Krahmer, Felix - TU Munich, Germany
- Maly, Johannes - Ludwig-Maximilians-Universität München, Germany
- Mixon, Dustin - Ohio State University, USA
- Peyré, Gabriel - École Normale Supérieure, France
- Pfander, Götz - KU Eichstätt-Ingolstadt, Germany
- Schnass, Karin - University of Innsbruck, Austria
- Vershynin, Roman - University of California, Irvine, USA
- Ward, Rachel - University of Texas at Austin, US
Preliminary program
This schedule is preliminary and could be updated.
Thursday, June 15
| 14:00 ~ 15:00 | Data-driven regularization for inverse problems - the dos and don‘ts Carola-Bibiane Schönlieb - University of Cambridge, United Kingdom |
| 15:00 ~ 15:30 | Max filtering Dustin Mixon - The Ohio State University, USA |
| 15:30 ~ 16:00 | Are neural operators really neural operators? Rima Alaifari - ETH Zurich, Switzerland |
| 16:30 ~ 17:00 | Completion of matrices with low description complexity Helmut Bölcskei - ETH Zurich, Switzerland |
| 17:00 ~ 17:30 | Mathematics of private synthetic data Roman Vershynin - University of California, Irvine, U.S.A. |
| 17:30 ~ 18:00 | What Makes Data Suitable for Deep Learning? Nadav Cohen - Tel Aviv University, Israel |
| 18:00 ~ 18:30 | A simple approach for quantizing neural networks Johannes Maly - LMU Munich, Germany |
Friday, June 16
| 14:00 ~ 15:00 | Feature learning in neural networks and kernel machines that recursively learn features Mikhail Belkin - UCSD, USA |
| 15:00 ~ 15:30 | Finite sample identification of neural networks Massimo Fornasier - Technical University of Munich, Germany |
| 15:30 ~ 16:00 | Convergence and error analysis of PINNs Claire Boyer - Sorbonne Université, |
| 16:30 ~ 17:00 | Private synthetic data March Boedihardjo - ETH Zurich, Switzerland |
| 17:00 ~ 17:30 | Convergence of MOD and ODL for dictionary learning Karin Schnass - Universität Innsbruck, Austria |
| 17:30 ~ 18:00 | Convergence of Entropy-Regularized Neural Natural Actor-Critic Semih Cayci - RWTH Aachen University, Germany |
| 18:00 ~ 18:30 | Robust low-rank matrix completion with adversarial noise Felix Krahmer - Technical University of Munich, Germany |
Saturday, June 17
| 14:00 ~ 15:00 | Physics-inspired learning on graphs Michael Bronstein - Oxford, UK |
| 15:00 ~ 15:30 | On the Training of Infinitely Deep and Wide ResNets Gabriel Peyré - CNRS and ENS, France |
| 15:30 ~ 16:00 | Hierarchical systems of exponential bases Götz Pfander - Catholic University Eichstätt-Ingolstadt, Germany |
| 16:30 ~ 17:00 | The separation capacity of random neural networks Sjoerd Dirksen - Utrecht University, The Netherlands |
| 17:00 ~ 17:30 | Three Vignettes in Computational Optimal Recovery Simon Foucart - Texas A&M University, United States |
| 17:30 ~ 18:30 | Randomly pivoted Cholesky Joel Tropp - Caltech, USA |
Posters
- Ellipsoid Methods for Metric Entropy Rates Computations
Thomas Allard - ETH Zürich, Switzerland - Sampling in spaces of variable bandwidth generated via Wilson basis
Beatrice Andreolli - University of Vienna, Austria - Revisiting RIP guarantees for sketching operators on mixture models
Ayoub Belhadji - ENS de Lyon, France - Theoretical guarantees for generative compressed sensing with subsampled isometries
Aaron Berk - McGill University, Canada - Analysing Implicit Bias/Regularisation via Invariant, Bregman Divergence, and Normalisation
Hung-Hsu Chou - Ludwig-Maximilians-Universität München, Germany - Line Search Methods for Deep Learning. It Could Work
Leonardo Galli - RWTH Aachen University, Germany - Advances in phaseless sampling of the short-time Fourier transform
Lukas Liehr - University of Vienna, Austria - Accelerated Griffin-Lim algorithm: A fast and provably convergent numerical method for phase retrieval
Rossen Nenov - Austrian Academy of Sciences, Austria - Gradient Descent and Stochastic Gradient Descent convergence for Learning Linear Neural Networks
Gabin Maxime Nguegnang - RWTH Aachen University, Germany - Essential duals using alternate frame operators
Mitra Shamsabadi - Acoustics Research Institute, Austrian Academy of Sciences, Austria - Upper and lower bounds for strong basins of attractions of non-convex sparse spike estimation
Yann Traonmilin - CNRS, Institut de mathématiques de Bordeaux, France