Contact
+49 711 685 66305
+49 711 685 67735
Email
Pfaffenwaldring 9
70569 Stuttgart
Germany
Room: 3.234
Office Hours
on appointment
Subject
Control theory is a well-established field whereas Machine Learning has gained popularity only recently. I am interested in using the experience in control theory to find guarantees for ML tools, especially I am looking at the robustness of Neural Networks.
P. Pauli, D. Gramlich, F. Allgöwer. Lipschitz constant estimation for general neural network architectures using control tools, 2024. [preprint]
P. Pauli, D. Gramlich, F. Allgöwer. State space representations of the Roesser type for convolutional layers. In 26th International Symposium on Mathematical Theory of Networks and Systems (MTNS), accepted, 2024. [preprint]
P. Pauli, A. Havens, A. Araujo, S. Garg, F. Khorrami, F. Allgöwer, B. Hu. Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations, In International Conference on Learning Representations (ICLR), 2024. [available online]
P. Pauli, R. Wang, I. R. Manchester, F. Allgöwer. Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian, In 62nd IEEE Conference on Decision and Control (CDC), 2023. [available online]
D. Gramlich, P. Pauli, C. W. Scherer, F. Allgöwer, C. Ebenbauer. Convolutional Neural Networks as 2-D systems, 2023. [preprint]
P. Pauli, D. Gramlich, F. Allgöwer. Lipschitz constant estimation for 1D convolutional neural networks. In Learning for Dynamics & Control Conference, 2023 (oral presentation). [available online]
P. Pauli, J. Berberich, F. Allgöwer. Robustness analysis and training of recurrent neural networks using dissipativity theory. In at-Automatisierungstechnik, vol. 70, no. 8, 2022, pp. 730-739, doi: 10.1515/auto-2022-0032. [available online]
P. Pauli, N. Funcke, D. Gramlich, M. A. Msalmi, F. Allgöwer. Neural network training under semidefinite constraints. In 61st IEEE Conference on Decision and Control (CDC), 2022. [available online]
P. Pauli, D. Gramlich, J. Berberich, F. Allgöwer. Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers. In 60th IEEE Conference on Decision and Control (CDC), 2021. [available online]
P. Pauli, J. Köhler, J. Berberich, A. Koch, F. Allgöwer. Offset-free setpoint tracking using neural network controllers. In Learning for Dynamics & Control Conference, 2021. [available online]
P. Pauli, A. Koch, J. Berberich, P. Kohler, F. Allgöwer. Training robust neural networks using Lipschitz bounds. In IEEE Control Systems Lett., 2021, doi: 10.1109/LCSYS.2021.11.3050444. [available online]
J. Köhler, L. Schwenkel, A. Koch, J. Berberich, P. Pauli, F. Allgöwer. Robust and optimal predictive control of the COVID-19 outbreak. Annual Reviews in Control, 2020, ISSN 1367-5788, doi: 10.1016/j.arcontrol.2020.11.002. [available online]
P. Pauli, A. Koch, F. Allgöwer. Smartphone Apps for Learning Progress and Course Revision. In Proc. 21st IFAC World Congress, vol. 53, no. 2, Berlin, Germany, 2020, pp. 17368-17373. [available online]
A. Koch, M. Lorenzen, P. Pauli, F. Allgöwer. Facilitating learning progress in a first control course via Matlab Apps. In Proc. 21st IFAC World Congress, vol. 53, no. 2, Berlin, Germany, 2020, pp. 17356-17361. [available online]
P. Pauli, S. M. Dibaji, A. M. Annaswamy, A. Chakrabortty. Optimal Delay Assignment for Delay-Aware Control of Cyber-Physical Systems: A Machine Learning Approach. In 58th IEEE Conference on Decision and Control (CDC), Nice, France, 2019. [available online]
R. Henriquez-Auba, P. Pauli, D. Kalathil, D.S. Callaway, K. Poolla. The Sharing Economy for Residential Solar Generation. In 57th IEEE Conference on Decision and Control (CDC), Miami, FL, USA, 2018. [available online]
|
SS 2019 |
|
|
WS 2019/20 |
Vortragsübungen und Vorlesungsorganisation: Einführung in die Regelungstechnik |
|
SS 2020 |
|
|
WS 2020/21 |
Vortragsübungen und Vorlesungsorganisation: Einführung in die Regelungstechnik |
|
SS 2021 |
|
|
WS 2021/22 |
Vortragsübungen und Vorlesungsorganisation: Einführung in die Regelungstechnik |
|
SS 2022 |
|
|
SS 2023 |
|
since 05/2019 |
Research Assistant at the Institute for Systems Theory and Automatic Control, University of Stuttgart |
|
08/2022 − 11/2022 |
Visiting Research stay at Australian Centre for Field Robotics, University of Sydney |
|
10/2015 − 04/2019 |
Master studies in Mechanical Engineering and Computational Engineering at Technical University of Darmstadt Master thesis: "Learning-based Optimization of Delay-Aware Control Designs for Wide-Area Oscillation Damping in Power Systems" at the Active-Adative Control Laboratory at Massachusetts Institute of Technology. |
|
07/2017 − 09/2017 |
Intership at Diesel Gasoline Systems, Robert Bosch GmbH, Feuerbach Topic: Parameter Identification for Sensor Models |
|
08/2016 - 05/2017 |
Exchange Year at University of California, Berkeley |
|
10/2012 − 09/2015 |
Bachelor studies in Mechanical Engineering at Technical University of Darmstadt Bachelor thesis: "Numerical and Experimental Investigations on a bistable Energy Harvester" at Dynamics and Vibrations Group at Technical University of Darmstadt |
|
09/2014 - 01/2015 |
Erasmus at Universidad Politécnica de Madrid |