Depending on the speaker, the talks will take place in Room KGA-303 or via Zoom (cf. invitation mails).

• 03.05.2022: Christian Kümmerle, "Dictionary-Sparse Recovery From Heavy-Tailed Measurements"
• 17.05.2022: Günther Wirsching, "Quantum-Inspired Uncertainty Quantification"
• 24.05.2022: Laura Thesing, "Which networks can be learned by an algorithm? - Expressivity meets Turing in Deep Learning"
• 14.06.2022: Yizhe Zhu, "Non-backtracking spectral clustering in sparse hypergraphs"
• 21.06.2022: Axel Böhm, "On min-max problems and finding weak Minty solutions"
• 23.06.2022: (Joint KU-LMU-TUM Seminar)
• 28.06.2022: Rishabh Dudeja, "Computational Lower Bounds for Tensor PCA"
• 12.07.2022: Hung-Hsu Chou, "Generalization and Magnification of Implicit Regularization"
• 21.07.2022: (Joint KU-LMU-TUM Seminar)
• 04.08.2022: (Joint KU-LMU-TUM Seminar)
• 09.09.2022: Hrushikesh Mhaskar, "Kernel based approximation"

Due to the current situation, the talks in the summer term will be held via Zoom.

• 19.10.2021: Get-together
• 26.10.2021: Hidde Schönberger, "Fractional Integrals and Supremals: Characterization of Lower Semicontinuity and Relaxation"
• 02.11.2021: Andrei Caragea, "Hierarchical exponential Riesz bases"
• 09.11.2021: Valerio Pagliari, "A homogenization problem inspired by high-contrast materials"
• 16.11.2021: Johannes Krebs, "Statistical topological data analysis"
• 23.11.2021: Jona Lelmi, "Large data limit for the MBO scheme for data clustering: Gamma-convergence of the thresholding energies"
• 25.11.2021: Dominik Stöger, "Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction" + Felix Voigtländer, "The universal approximation theorem for complex-valued neural networks" (Joint KU-LMU-TUM seminar)
• 07.12.2021: Ekkehard Schnoor, "Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks"
• 14.12.2021: Christmas celebration of KU -> Cancelled...
• 11.01.2022: Martin Genzel, "The Separation Capacity of Random Neural Networks"
• 18.01.2022: Konstantin Riedl, "Mean-Field Law Global Convergence of Consensus-Based Optimization"
• 20.01.2022: Cristina Cipriani, "A Mean-Field Optimal Control Approach to the Training of NeurODEs" + Olga Graf, "One-bit unlimited sampling" (Joint KU-LMU-TUM seminar)
• 25.01.2022: Frank Filbir, "Shift Invariant Spaces related to the Special Affine Fourier Transform"
• 01.02.2022: Hans-Christian Jung, "Learning interesting probability distributions"
• 24.02.2022: Adalbert Fono, "Limitations of Deep Learning on Digital Hardware" + Sohir Maskey, "Stability and Generalization Capabilities of Message Passing Graph Neural Networks" (Joint KU-LMU-TUM seminar)
• 01.03.2022: Theophil Trippe, "Learning to Invert Defocus Blur: A Data-Driven Approach to the 'Helsinki Deblur Challenge'"
• 29.03.2022: Marco Morandotti, "Minimisers of the Canham-Helfrich functional in the space of generalised Gauss graphs"

Due to the current situation, the talks in the summer term will be held via Zoom.

• 20.04.2021: Organizational meeting
• 22.04.2021: Dae Gwan Lee, "A quantitative approximation result for complex-valued neural networks and applications" + Johannes Maly, "Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank" (joint KU-LMU-TUM seminar)
• 04.05.2021: Dominik Stöger, "Understanding overparameterization in low-rank matrix recovery and generative adversarial networks"
• 11.05.2021: Hung-Hsu Chou, "Overparameterization and generalization error: weighted trigonometric interpolation"
• 18.05.2021: Dominik Engl, "Theories for incompressible strings and rods: a rigorous derivation via Γ-convergence"
• 01.06.2021: Ursula Molter, "Tiles, Multi-tiles, Riesz bases of exponentials and the Bohr topology"
• 15.06.2021: Claudio Verdun, "How to impute data and complete matrices if you must"
• 22.06.2021: Gabin Maxime Nguegnang, "Convergence of Gradient Descent in Learning Deep Linear Networks"
• 29.06.2021: Antonella Ritorto, "Asymptotic analysis of rigidity constraints modeling fiber-reinforced composite"
• 13.07.2021: Carolin Kreisbeck, "Nonlocal variational problems: Structure-preservation during relaxation?"
• 20.07.2021: Patrik Hammer, "Universal approximation results in the theory of neural networks"

• 10.11.2020: Johannes Maly, "Gradient Descent for Deep Matrix Factorizations"
• 08.12.2020: Sjoerd Dirksen, "Covariance estimation under one-bit quantization"
• 22.12.2020: Javier Cueto, "Vector Variational Problems based on Fractional and Nonlocal Gradients. Applications to Solid Mechanics"
• 12.01.2021: Dmitry Yarotsky, "Approximations with deep neural networks"
• 26.01.2021: Timo Klock, "Deep neural networks adapt to intrinsic dimensionality beyond the data domain"
• 02.02.2021: Diyora Salimova, "Space-time deep neural network approximations for high-dimensional PDEs"
• 16.02.2021: Michael Rauchensteiner, "Stable Recovery of Entangled Weights: Towards Robust
  Identification of Deep Neural Networks"

• 09.04.2020: Dr. Michael Speckbacher
• 07.05.2020: Dr. Wolfgang Erb (KU Eichstätt-Ingolstadt), Anisotropic N-term approximation with Gaussians
• 26.05.2020: Prof. Radu Balan (University of Maryland, USA), Permutation invariant representations and graph deep learning - Part 1
• 01.06.2020: Public Holiday
• 08.06.2020: Prof. Marcin Bownik (University of Oregon, USA), Exponential frames and syndetic Riesz sequences, 6:00 pm (Time in Germany)
• 15.06.2020: Prof. Radu Balan (University of Maryland, USA), Permutation invariant representations and graph deep learning - Part 2
• 22.06.2020: Prof. Philippe Jaming (Université de Bordeaux, France), Mobile and diffusive sampling
• 06.07.2020: Prof. Shahaf Nitzan (Georgia Institute of Technology, USA), Uncertainty Principles for Fourier Multipliers
• 20.07.2020: Franziska Schlamp (KU Eichstätt-Ingolstadt), Presentation about internship at Airbus