Prof. Dr. Simon Weißmann
Business Informatics and Mathematics
B 6, 26
Mathematical Institute – Room 3.05
68159 Mannheim
Short CV
- since 2023, Assistant Professor (W1), University of Mannheim
- 2020–2023, Postdoc with Prof. Jakob Zech, Heidelberg University
- 2017–2020, PhD supervised by Prof. Claudia Schillings, University of Mannheim
- 2017–2020, member of the research training group Statistical Modeling of Complex Systems and Processes, Heidelberg-Mannheim
- 2012–2017, Studies of Business Mathematics, University of Mannheim
Research Interests
- (Bayesian) Inverse Problems
- (Stochastic) Optimization
- (Ensemble) Kalman Filtering
- Monte Carlo methods
- Rare event simulation
- Application in Machine Learning
Teaching
Lectures
| University of Mannheim | |
| HWS 2024 | Optimization in Machine Learning (BSc/MSc) |
| FSS 2024 | Inverse Problems (MSc) |
HWS 2023 | Mathematical Finance (BSc) |
| HWS 2023 | Reinforcement Learning 2 (MSc) joint with L. Döring and M. Staudigl |
| FSS 2023 | Optimization in Machine Learning (BSc/MSc) |
Lecture Notes:
- Optimization in Machine Learning (latest update: 09.09.2024)
Seminars
| University of Mannheim | |
| HWS 2024 | Advanced Seminar on Mathematical methods in Artificial Intelligence (BSc/MSc) |
| FSS 2024 | Mathematical Optimization (BSc/MSc) |
| HWS 2023 | Advanced Seminar on Mathematical methods in Artificial Intelligence (BSc/MSc) |
| Heidelberg University | |
WiSe 2021 | Simulation of Stochastic Systems (BSc/MSc) |
Publications
Preprints and submitted manuscripts
| 2025 | Clustered KL-barycenter design for policy evaluation S. Weissmann, T. Freihaut, C. Vernade, G. Ramponi and L. Döring Submitted |
| 2024 | Derivative-free stochastic optimization for inverse problems M. Staudigl, S. Weissmann and T. van Leeuwen Preprint: arxiv:2411.18100 Structure Matters: Dynamic Policy Gradient S. Klein, X. Zhang, T. Başar, S. Weissmann and L. Döring Preprint: arxiv:2411.04913 Polyak's heavy ball method achieves accelerated local rate of convergence under Polyak-Lojasiewicz inequality S. Kassing and S. Weissmann Preprint: arxiv:2410.16849 On the mean field limit of consensus based methods M. Koß, S. Weissmann and J. Zech Preprint: arXiv:2409.03518 Almost sure convergence rates of stochastic gradient methods under gradient domination S. Weissmann, S. Klein, W. Azizian and L. Döring Preprint: arXiv:2405.13592 On the mean-field limit for Stein variational gradient descent: stability and multilevel approximation S. Weissmann and J. Zech Preprint: arXiv:2402.01320 |
Articles in journals and refereed proceedings volumes
| 2025 | Metropolis-adjusted interacting particle sampling B. Sprungk, S. Weissmann and J. Zech Statistics and Computing (accepted) Preprint: arXiv:2312.13889 |
2024 | The ensemble Kalman filter for dynamic inverse problems S. Weissmann, N. Chada and X. Tong Information and Inference: A Journal of the IMA, Volume 13, Issue 4, doi: 10.1093/imaiai/iaae030 Adaptive multilevel subset simulation with selective refinement D. Elfverson, R. Scheichl, S. Weissmann and F. A. DiazDelaO SIAM/ On the ensemble Kalman inversion under inequality constraints M. Hanu and S. Weissmann Inverse Problems, Volume 40, Number 9, doi: 10.1088/1361-6420/ad6a33 One-shot learning of surrogates in PDE-constrained Optimization under Uncertainty P. Guth, C. Schillings and S. Weissmann SIAM/ Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods S. Klein, S. Weissmann and L. Döring In: The Twelfth International Conference on Learning Representations (ICLR) 2024 Preprint: arXiv:2310.02671 |
| 2022 | Continuous time limit of the stochastic ensemble Kalman inversion: Strong convergence analysis D. Blömker, C. Schillings, P. Wacker and S. Weissmann SIAM Journal on Numerical Analysis, Volume 60, Issue 6, doi: 10.1137/21M1437561 Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models S. Weissmann Inverse Problems, Volume 38, Number 10, doi: 10.1088/1361-6420/ac8bed Multilevel optimization for inverse problems S. Weissmann, A. Wilson and J. Zech Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), PMLR 178:5489-5524 Adaptive Tikhonov regularization for stochastic ensemble Kalman inversion S. Weissmann, N. Chada, C. Schillings and X. Tong Inverse Problems, Volume 38, Number 4, doi: 10.1088/1361-6420/ac5729 Consistency analysis of bilevel data-driven regularization in inverse problems N. Chada, C. Schillings, X. Tong and S. Weissmann Communications in Mathematical Sciences, Volume 20, Number 1, doi: 10.4310/CMS.2022.v20.n1.a4 |
| 2021 | Ensemble Kalman filter for neural network based one-shot inversion P. Guth, C. Schillings and S. Weissmann In: Optimization and Control for Partial Differential Equations, De Gruyter, doi: 10.1515/9783110695984-014 Fokker–Planck particle systems for Bayesian inference: computational approaches S. Reich and S. Weissmann SIAM/ Well posedness and convergence analysis of the ensemble Kalman Inversion D. Blömker, C. Schillings, P. Wacker and S. Weissmann Inverse Problems, Volume 35, Number 8, doi: 10.1088/1361-6420/ab149c On the incorporation of box-constraints for ensemble Kalman Inversion N. Chada, C. Schillings and S. Weissmann Foundations of Data Science, Volume 1, Issue 4, doi: 10.3934/fods.2019018 |
Theses
| 2020 | Particle based sampling and optimization methods for inverse problems S. Weissmann Dissertation, University of Mannheim, link |
2017 | Perpetual Integrals for stochastic processes S. Weissmann Master Thesis, University of Mannheim |
| 2015 | Renewal processes – Alternation, excesslife and agedistribution S. Weissmann Bachelor Thesis, University of Mannheim |