Dominik Stöger
 |
Dominik Stöger KU Eichstätt-Ingolstadt |
Since 2021, I have been an Assistant Professor (tenure-track) at KU Eichstätt-Ingolstadt at the Department of Mathematics, affiliated with MIDS. Before this role, I was a postdoctoral researcher at USC from 2019 to 2021, where I was mentored by Mahdi Soltanolkotabi. I completed my Ph.D. in Mathematics at the Technical University of Munich in 2019 under the supervision of Felix Krahmer. I also obtained my MSc and BSc degrees in Mathematics from the Technical University of Munich in 2015 and 2013, respectively.
My research interests lie in the mathematical foundations of data science. These include non-convex optimization problems in machine learning and signal processing, understanding overparameterization in modern machine learning models, and low-rank matrix recovery problems. To study these topics I often combine tools from optimization and high-dimensional probability.
A longer CV can be found here (last updated May 2024).
News:
11/2023: new preprint On the Lipschitz constant of random neural networks joint with Paul Geuchen, Thomas Heindl, and Felix Voigtlaender
06/2023: my paper on Robust recovery of low-rank matrices and low-tubal-rank tensors from noisy sketches, joint with Anna Ma and Yizhe Zhu, was accepted for publication by the SIAM Journal on Matrix Analysis and Applications
05/2023: my paper on Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing with Mahdi Soltanolkotabi and Changzhi Xie was accepted for publication in COLT 2023
04/2023: my paper on Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing, joint with Kiryung Lee, was accepted for publication by the SIAM Journal on Mathematics of Data Science
03/2023: new preprint on How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise? with Julia Kostin and Felix Krahmer