Publications

See also my Google Scholar profile.

Christian Kümmerle, Johannes Maly (2023). Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares. NeurIPS 2023.

Cite arXiv

Liangzu Peng, Christian Kümmerle, René Vidal (2023). On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation. CVPR 2023 (Highlighted, top 2.5% of submitted papers).

PDF Cite Code Poster PDF w/ supplementary material

Christian Kümmerle, Mauro Maggioni, Sui Tang (2022). Learning Transition Operators From Sparse Space-Time Samples. arXiv:2212.00746.

Cite arXiv

Liangzu Peng, Christian Kümmerle, René Vidal (2022). Global Linear and Local Superlinear Convergence of IRLS for Non-Smooth Robust Regression. NeurIPS 2022.

Cite Code Poster PDF arXiv

Felix Krahmer, Christian Kümmerle, Oleh Melnyk (2022). On the robustness of noise-blind low-rank recovery from rank-one measurements. Linear Algebra Appl., 652, 37-81.

PDF Cite arXiv

Olivier Guédon, Felix Krahmer, Christian Kümmerle, Shahar Mendelson, Holger Rauhut (2022). On the geometry of polytopes generated by heavy-tailed random vectors. Commun. Contemp. Math., 24(03), 2150056.

PDF Cite arXiv

Pedro Abdalla, Christian Kümmerle (2022). Dictionary-Sparse Recovery From Heavy-Tailed Measurements. Inf. Inference, 11(4), 1501–1526.

PDF Cite arXiv

Christian Kümmerle, Claudio Mayrink Verdun, Dominik Stöger (2021). Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate. NeurIPS 2021 (Spotlight, top 3% of submitted papers).

PDF Cite Link to Proceedings arXiv

Christian Kümmerle, Claudio Mayrink Verdun (2021). A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples. ICML 2021.

PDF Cite Code Poster Link to Proceedings Slides

Christian Kümmerle, Claudio Mayrink Verdun (2020). Escaping Saddle Points in Ill-Conditioned Matrix Completion with a Scalable Second Order Method. In Workshop on Beyond First Order Methods in ML Systems at ICML 2020.

PDF Cite Code

Christian Kümmerle (2019). Understanding and Enhancing Data Recovery Algorithms - From Noise-Blind Sparse Recovery to Reweighted Methods for Low-Rank Matrix Optimization. Ph.D. Dissertation, TU Munich, 2019.

PDF Cite mediaTUM

Christian Kümmerle, Claudio Mayrink Verdun (2019). Completion of Structured Low-Rank Matrices via Iteratively Reweighted Least Squares. In SampTA 2019, pp. 1-5.

PDF Cite DOI

Christian Kümmerle, Claudio Mayrink Verdun (2018). Denoising and Completion of Structured Low-Rank Matrices via Iteratively Reweighted Least Squares. In Proceedings of iTWIST'18.

PDF Cite arXiv

Christian Kümmerle, Juliane Sigl (2018). Harmonic Mean Iteratively Reweighted Least Squares for Low-Rank Matrix Recovery. J. Mach. Learn. Res., 19(47), 1815-1863.

PDF Cite Code arXiv

Felix Krahmer, Christian Kümmerle, Holger Rauhut (2018). A Quotient Property for Matrices with Heavy-Tailed Entries and its Application to Noise-Blind Compressed Sensing. arXiv:1806.04261.

Cite arXiv

Christian Kümmerle, Juliane Sigl (2017). Harmonic Mean Iteratively Reweighted Least Squares for Low-Rank Matrix Recovery. In SampTA 2017, pp. 489-493.

PDF Cite Code