Research Group Holger Rauhut
Holger Rauhut
Prof. Dr.
Core PI
Holger Rauhut
is Professor of Mathematical Data Science and Artificial Intelligence at LMU Munich.
His focus on the intersection of mathematics and artificial intelligence, aiming for both a mathematical understanding of artificial intelligence and artificial intelligence for mathematical problems.
Team members @MCML
PostDocs
Sakirudeen Abdulsalaam
Dr.
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Leonardo Galli
Dr.
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Ulrich Terstiege
Dr.
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Tizian Wenzel
Dr.
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
PhD Students
Wiebke Bartolomaeus
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Kurt Izak Cabanilla
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Arinze Lawrence Folarin
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Garam Kim
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Laura Paul
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Shan Wei
→ Group Holger Rauhut
Mathematical Data Science and Artificial Intelligence
Recent News @MCML
Publications @MCML
2026
Flatland: The Adventures of Gradient Descent with Large Step Sizes.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
The Riemannian Geometry associated to Gradient Flows of Linear Convolutional Networks.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. To be published. Preprint available. arXiv
Piecewise linear interpolation via kernels.
Preprint (Mar. 2026). arXiv
PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Error.
Preprint (Feb. 2026). arXiv
Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings.
Preprint (Feb. 2026). arXiv
Convergence of gradient flow for learning convolutional neural networks.
Preprint (Jan. 2026). arXiv
Sharp inverse statements for kernel approximation: Superconvergence and saturation.
Preprint (Jan. 2026). arXiv
On the optimal shape parameter for kernel methods: Sharp direct and inverse statements.
Preprint (Jan. 2026). arXiv
2025
Sobolev Algorithm for Local Smoothness Analysis (SALSA) via Sharp Direct and Inverse Statements.
Preprint (Dec. 2025). arXiv
Rank-sparsity decomposition for planted quasi clique recovery.
Journal of Global Optimization. Nov. 2025. DOI
Numerical Analysis of Mask-Based Phase Reconstruction in Phaseless Spherical Near-Field Antenna Measurements.
Sensors 25.18. Sep. 2025. DOI
General superconvergence for kernel-based approximation.
Preprint (May. 2025). arXiv
2024
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. DOI
Imaging with Confidence: Uncertainty Quantification for High-dimensional Undersampled MR Images.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI GitHub
With or Without Replacement? Improving Confidence in Fourier Imaging.
CoSeRa 2024 - International Workshop on the Theory of Computational Sensing and its Applications to Radar, Multimodal Sensing and Imaging. Santiago de Compostela, Spain, Sep 18-20, 2024. DOI
Convergence of gradient descent for learning linear neural networks.
Advances in Continuous and Discrete Models 2024.23. Jul. 2024. DOI
2023
Uncertainty Quantification For Learned ISTA.
MLSP 2023 - IEEE Workshop on Machine Learning for Signal Processing. Rome, Italy, Sep 17-20, 2023. DOI
Uncertainty quantification for sparse Fourier recovery.
Preprint (Sep. 2023). arXiv
Sampling Strategies for Compressive Imaging Under Statistical Noise.
SampTA 2023 - 14th International Conference on Sampling Theory and Applications. Yale, CT, USA, Jul 10-14, 2023. DOI
Robust implicit regularization via weight normalization.
Preprint (May. 2023). arXiv
©all images: LMU | TUM
2024-12-27 - Last modified: 2026-05-01