MS. Samira Kabri
Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY
PhD student in Mathematics in the Computational Imaging Group at DESY, led by Martin Burger.
I am primarily interested in solving inverse problems with data-driven strategies where I focus on analyzing their stability and convergence behavior. Since these properties are strongly connected to the continuum limit of discretized problems, I am particularly interested in learning architectures that can be interpreted in an infinite-dimensional setting (like Fourier Neural Operators or spectral filters).
In general, I like analysing simple, foundational concepts very detailed to obtain valuable insights for the bigger, more complex, picture. :)
Publications
Convergent Data-Driven Regularizations for CT Reconstruction
Kabri S, Auras A, Riccio D, Bauermeister H, Benning M, Moeller M, Burger M - Communications on Applied Mathematics and Computation - 2024
Resolution-Invariant Image Classification Based on Fourier Neural Operators
Kabri S, Roith T, Tenbrinck D, Burger M - Lecture Notes in Computer Science - 2023