- Demystifying Linear Operator Learning for Control Systems. IEEE Conference on Decision and Control , 2026, 8 more…
- Koopman-Equivariant Gaussian Processes. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research 258), 2025, 3151--3159 more…
- Operator Models for Continuous-Time Offline Reinforcement Learning. TUM Lehrstuhl für Informationstechnische Regelung (Prof. Hirche), 2025, more…
- Sequence Modeling with Spectral Mean Flows. The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025 more…
- Koopman Kernel Regression. Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (NeurIPS Proceedings), 2023 more…
- Diffeomorphically Learning Stable Koopman Operators. IEEE Control Systems Letters (L-CSS) 6, 2022, 3427 - 3432 more…
- Towards Data-driven LQR with Koopmanizing Flows. IFAC-PapersOnLine, 20226th IFAC Conference on Intelligent Control and Automation Sciences ICONS 2022: Cluj-Napoca, Romania, 13–15 July 2022, 13-18 more…
Max Beier
Postal address
Barerstr. 21
80333 München
- Office hours: nach Vereinbarung
- Room: 0305.04.509
- E-mail: max.beier@tum.de
Short Biography
| Seit 05/2024 | Associate PhD |
| Since 11/2023 | Research Assistent Chair of Information-oriented Control Technical University of Munich |
| 10/2020-07/2023 | Master of Science - Robotics, Cognition, Intelligence Technical University of Munich Focus: Machine Learning for Dynamical Systems and Control |
| 10/2017-09/2020 | Bachelor of Engineering - Mechanical Engineering Baden-Wuerttemberg Cooperative State University (DHBW) Stuttgart Robert Bosch GmbH |
Research Interests
- Principled Machine Learning
- Dynamical Systems and Operator Theory
- Learning-based Control
My research focuses on learning-based dynamical system representations that enable the automated design with performance guarantees for a downstream task; for example, predicting and controlling a robotic system. To this end, I am especially interested in geometric and operator-theoretic methods. Through fruitful collaboration, I have applied these mathematical ideas to time series forecasting, sequence modeling, and optimal control. Here is a short pitch of the research in this direction at ITR.
According to my publications my topics of study are the ones on the right.
Contact
I am always looking forward to working with motivated students. If you are curious about my research and looking for a thesis, do not hesitate to contact me. If there is no topic on display, please specify which topics you are interested in. Please include your CV, a current transcript of records, and your preferred start date.
Active Learning in Dynamical Systems
Type: Guided Research / Master's Thesis
Prerequisites:
- Knowledge in machine learning/ statistics or dynamical systems
- Good coding skills in Python and a linear algebra and numerics framework (preferably JAX)
Description:
Within the ALeSCo consortium an intersectional project is P6: Benchmarks for Active Learning in Systems and Control. Within this project we are developing a benchmark for active learning algorithms in dynamical systems. There are multiple subtasks that can be tackled in the course of a research project or thesis. These include deriving principled assessment metrics, designing and implementing a benchmark architecture and environments, as well as implementing and evaluating experimental and state-of-the-art active learning algorithms.
References:
Active learning in robotics: A review of control principles