SPP 2298:  Theoretical Foundations of Deep Learning

• Subject Area: Mathematics ; Computer Science, Systems and Electrical Engineering ; Materials Science and Engineering ; Medicine ; Physics
• Term: since 2021
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 441826958

The Priority Programm (PP) "Theoretical Foundations of Deep Learning" will be coordinated at LMU Munich. This includes organizing the various planned collaborating and networking activities such as the annual conferences, workshops, mini-tutorials, and winter schools, coordinating the selection and invitation of PP Visiting Professors and PP Fellows, setting up and maintaining a webpage, as well as providing a newsletter and hosting a preprint server. Also, all PR activities require organization. In addition, we aim to promote early career scientists and female researchers by various measures, which need to be coordinated.

• DFG Programme: Priority Programmes
• International Connection: Austria, Canada, France, United Kingdom, USA

Projects

• Accelerating Diffusion Models Through Sparse Neural Networks (Applicant Lederer, Johannes )
• Adaptive Neural Tensor Networks for parametric PDEs (Applicants Eigel, Martin ;  Grasedyck, Lars )
• Assessment of Deep Learning through Meanfield Theory (Applicant Herty, Michael )
• Combinatorial and implicit approaches to deep learning - Phase II (Applicant Montúfar, Guido )
• Coordination Funds (Applicant Kutyniok, Gitta )
• Curse-of-dimensionality-free nonlinear optimal feedback control with deep neural networks: Spatially decaying sensitivity and non-smooth approximations (Applicant Grüne, Lars )
• Deep assignment flows for structured data labeling: design, learning and prediction performance (Applicant Schnörr, Christoph )
• Deep-Learning Based Regularization of Inverse Problems (Applicants Burger, Martin ;  Kutyniok, Gitta )
• Deep learning for non-local partial differential equations (Applicants Jentzen, Arnulf ;  Kutyniok, Gitta )
• Deep neural networks overcome the curse of dimensionality in the numerical approximation of stochastic control problems and of semilinear Poisson equations (Applicants Hutzenthaler, Martin ;  Kruse, Thomas )
• Enriching Deep Learning with Probability and Geometry (Applicant Hennig, Philipp )
• Generative Models for Bayesian Inverse Problems in Image Processing
• GeoMAR: Geometric Methods for Adversarial Robustness (Applicants Bungert, Leon ;  Schwinn, Ph.D., Leo )
• Globally Optimal Neural Network Training (Applicants Pfetsch, Marc Emanuel ;  Pokutta, Sebastian )
• Implicit Bias in Adversarial Training (Applicants Fornasier, Massimo ;  Rauhut, Holger )
• Improving deep learning techniques for sampling thermodynamic-equilibrium molecular dynamics with optimal transport (Applicant Friesecke, Gero )
• Multi-Phase Probabilistic Optimizers for Deep Learning (Applicant Hennig, Philipp )
• Multilevel Architectures and Algorithms in Deep Learning (Applicants Herzog, Roland ;  Schiela, Anton )
• Multiscale Dynamics of Neural Nets via Stochastic Graphops (Applicants Engel, Maximilian ;  Kühn, Ph.D., Christian )
• On the Convergence of Variational Deep Learning to Sums of Entropies (Applicants Fischer, Asja ;  Lücke, Jörg )
• Operator Learning for Optimal Control: Approximation and Statistical Theory (Applicants Herberg, Evelyn ;  Wang, Sven ;  Zech, Jakob )
• Optimal Transport and Measure Optimization Foundation for Robust and Causal Machine Learning (Applicant Zhu, Jia-Jie )
• Provable Robustness Certification of Graph Neural Networks (Applicant Günnemann, Stephan )
• Robust and Interpretable Learned Regularization for Solving Inverse Problems in Medical Imaging (Applicants Kobler, Erich ;  Neumayer, Sebastian )
• Solving linear inverse problems with neural networks: generalization, robustness, uncertainty quantification (Applicants Heckel, Reinhard ;  Krahmer, Ph.D., Felix )
• Spiking Neural Networks: Theoretical Foundations, Trustworthiness, and Energy-Efficiency (Applicants Boche, Holger ;  Kutyniok, Gitta )
• Statistical Foundations of Semi-supervised Learning with Graph Neural Networks (Applicant Ghoshdastidar, Ph.D., Debarghya )
• Structure-preserving deep neural networks to accelerate the solution of the Boltzmann equation (Applicants Frank, Martin ;  Krumscheid, Sebastian )
• Theoretical Foundations of Uncertainty-Aware Deep Learning for Inverse Problems (Applicants Burger, Martin ;  Möller, Michael )
• Theory of Deep Anomaly Detection (Applicant Kloft, Marius )
• Towards a Statistical Analysis of DNN Training Trajectories (Applicant Steinwart, Ingo )
• Towards everywhere reliable classification - A joint framework for adversarial robustness and out-of-distribution detection (Applicant Hein, Matthias )
• Uncertainty Guarantees for Graph Neural Networks (Applicant Bojchevski, Aleksandar )

• Spokesperson: Professorin Dr. Gitta Kutyniok