Applied Mathematics

Fabian Altekrüger

Kontakt

Technische Universität Berlin
Institut für Mathematik

Straße des 17. Juni 136
10623 Berlin

Room MA 479
Tel.: +49 - (0)30 - 314-28036
Email: altekrueger (at) math.tu-berlin.de, fabian.altekrueger (at) hu-berlin.de
Profiles: Github, Google Scholar

Secretary MA 4-3 Julia Wilton
Room MA 476 Email: wilton (at) math.tu-berlin.de

Publications

F. Altekrüger, J. Hertrich and G. Steidl (2023).
Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels.
International Conference on Machine Learning 2023.
Proceedings of Machine Learning Research, vol. 202, pp. 664-690.
[www], [arxiv], [Code]

F. Altekrüger and J. Hertrich (2023).
WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution.
SIAM Journal on Imaging Sciences, vol. 16(3), pp. 1033-1067.
[doi], [arxiv], [Code]

J. Hertrich, C. Wald, F. Altekrüger and P. Hagemann (2023).
Generative Sliced MMD flows with Riesz kernels.
(arXiv Preprint#2305.11463)
[arxiv], [Code]

P. Hagemann, J. Hertrich, F. Altekrüger, R. Beinert, J. Chemseddine and G. Steidl (2023).
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel.
(arXiv Preprint#2310.03054)
[arxiv], [Code]

F. Altekrüger, A. Denker, P. Hagemann, J. Hertrich, P. Maass and G. Steidl (2023).
PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization.
Inverse Problems, vol. 39, no. 6.
[doi], [arxiv], [Code]

F. Altekrüger, P. Hagemann and G. Steidl (2023).
Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems.
Transactions on Machine Learning Research (TMLR)
[openreview]

A. Kofler, F. Altekrüger, F. A. Ba, C. Kolbitsch, E. Papoutsellis, D. Schote, C. Sirotenko, F. Zimmermann and K. Papafitsoros (2023).
Learning Regularization Parameter-Maps for Variational Image Reconstruction using Deep Neural Networks and Algorithm Unrolling
Accepted in SIAM Journal of Imaging Sciences (arXiv Preprint#2301.05888)
[arxiv]