Publications

Preprints:

1. D. Stöger and Y. Zhu. Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity
   [preprint]

2. P. Geuchen, T. Heindl, D. Stöger, and F. Voigtlaender. On the Lipschitz constant of random neural networks
   [preprint]

3. H. Chou, J. Maly, and D. Stöger. How to induce regularization in generalized linear models: A guide to reparametrizing gradient flow
   [preprint]

4. J. Kostin, F. Krahmer, and D. Stöger. How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?
   [preprint]

Refereed journal articles and machine learning conference proceedings:

1. A. Ma, D. Stöger, and Y. Zhu. Robust recovery of low-rank matrices and low-tubal-rank tensors from noisy sketches
   SIAM Journal on Matrix Analysis and Applications (SIMAX), 2023
   [Journal][preprint]

2. K. Lee and D. Stöger. Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing.
   SIAM Journal on Mathematics of Data Science (SIMODS), 2023
   [Journal][preprint] [Slides]

3. M. Soltanolkotabi, D. Stöger, C. Xie. Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing.
   COLT 2023
   [COLT][preprint] [Slides]

4. D. Stöger and M. Soltanolkotabi. Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction.
   NeurIPS 2021
   [full paper] [NeurIPS version] [Slides]

5. C. Kümmerle, C. Mayrink Verdun, and D. Stöger. Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate.
   NeurIPS 2021 (Spotlight, top 3% of submitted papers)
   [full paper] [NeurIPS version]

6. Y. Balaji, M. Sajedi, N. Kalibhat, M. Ding, D. Stöger, M. Soltanolkotabi, S. Feizi. Understanding Over-parameterization in Generative Adversarial Networks.
   ICLR 2021
   [Paper]

7. F. Krahmer and D. Stöger. On the convex geometry of blind deconvolution and matrix completion.
   Communications on Pure and Applied Mathematics, 2021
   [Journal][preprint]

8. F. Krahmer and D. Stöger. Complex phase retrieval from subgaussian measurements.
   Journal of Fourier Analysis and Applications, 2020
   [Journal][preprint]

9. F. Cagnetti, M. Perugini, and D. Stöger. Rigidity for perimeter inequality under spherical symmetrisation
   Calculus of Variations and Partial Differential Equations, 2020
   [Journal][preprint]

10. J. Geppert, F. Krahmer, and D. Stöger. Sparse Power Factorization: Balancing peakiness and sample complexity.
    Advances in Computational Mathematics, 2019.
    [Journal][preprint]

11. P. Jung, F. Krahmer, and D. Stöger. Blind demixing and deconvolution at near-optimal rate.
    IEEE Transactions on Information Theory, 2018
    [Journal][preprint]

Book Chapters:

1. T. Fuchs, D. Gross, P. Jung, F. Krahmer, R. Kueng, Dominik Stöger. Proof methods for robust low-rank matrix recovery
   Compressed Sensing in Information Processing. Birkhäuser, Cham, 2022. 37-75.
   [Book chapter][arXiv]

Conference proceedings:

1. C. Kümmerle and D. Stöger. "Linear Convergence of Iteratively Reweighted Least Squares for Nuclear Norm Minimization”. In: IEEE 13rd Sensor Array and Multichannel Signal Processing Workshop (SAM). IEEE. 2024.

2. F. Krahmer and D. Stöger. “Blind deconvolution: Convex geometry and noise robustness”. In: 52nd Annual Asilomar Conference on Signals, Systems, and Computers. IEEE. 2018.

3. D. Stöger, J. Geppert, and F. Krahmer. “Sparse power factorization with refined peakiness conditions”. In: 2018 IEEE Statistical Signal Processing Workshop (SSP). IEEE. 2018, pp. 816–820.

4. J. Geppert, F. Krahmer, and D. Stöger. “Refined performance guarantees for Sparse Power Factorization”. In: 12th International Conference on Sampling Theory and Applications (SampTA). IEEE. 2017, pp. 509–513.

5. D. Stöger, P. Jung, and F. Krahmer. “Blind demixing and deconvolution with noisy data at near optimal rate”. In: Wavelets and Sparsity XVII. Vol. 10394. International Society for Optics and Photonics. 2017, 103941E.

6. P. Jung, F. Krahmer, and D. Stoeger. “Blind Demixing and Deconvolution with Noisy Data: Near-optimal Rate”. In: 21st International ITG Workshop on Smart Antenna. 2017.

7. D. Stöger, P. Jung, and F. Krahmer. “Blind deconvolution and compressed sensing”. In: 2016 4th International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa). IEEE. 2016, pp. 24–27