Jerome Sieber

Jerome Sieber

Auto-generated profile, based on publicly available information

Jerome Sieber

ETH Zurich

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 May 2022 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
ADAlexandre Didier
Alexandre Didier
JSJerome Sieber
Jerome Sieber
MZMelanie N. Zeilinger
Melanie N. Zeilinger
We present an optimisation-based method for synthesising a dynamic regret optimal controller for linear systems with potentially adversarial disturbances and known or adversarial initial conditions. The dynamic regret is defined as the difference between the true incurred cost of the system and the cost which could have optimally been achieved under any input sequence having full knowledge of all future disturbances for a given disturbance energy. This problem formulation can be seen as an alternative to classical H2-or H∞-control. The proposed controller synthesis is based on the system level parametrisation, which allows reformulating the dynamic regret problem as a semi-definite problem. This yields a new framework that allows to consider structured dynamic regret problems, which have not yet been considered in the literature. For known pointwise ellipsoidal bounds on the disturbance, we show that the dynamic regret bound can be improved compared to using only a bounded energy assumption and that the optimal dynamic regret bound differs by at most a factor of 2π from the computed solution. Furthermore, the proposed framework allows guaranteeing state and input constraint satisfaction.

3 June 2021 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
JSJerome Sieber
Jerome Sieber
SBSamir Bennani
Samir Bennani
MZMelanie N. Zeilinger
Melanie N. Zeilinger
Robust tube-based model predictive control (MPC) methods address constraint satisfaction by leveraging an a priori determined tube controller in the prediction to tighten the constraints. This letter presents a system level tube-MPC (SLTMPC) method derived from the system level parameterization (SLP), which allows optimization over the tube controller online when solving the MPC problem, which can significantly reduce conservativeness. We derive the SLTMPC method by establishing an equivalence relation between a class of robust MPC methods and the SLP. Finally, we show that the SLTMPC formulation naturally arises from an extended SLP formulation and show its merits in a numerical example.

11 June 2022 in European Journal of Control
Verified
Journal Article
Open access
JSJerome Sieber
Jerome Sieber
AZAndrea Zanelli
Andrea Zanelli
SBSamir Bennani
Samir Bennani
MZMelanie N. Zeilinger
Melanie N. Zeilinger

13 December 2023
Verified
Conference Paper
Open access
ALAntoine P. Leeman
Antoine P. Leeman
JSJérôme Sieber
Jérôme Sieber
SBSamir Bennani
Samir Bennani
MZMelanie N. Zeilinger
Melanie N. Zeilinger
This paper addresses the problem of optimally controlling nonlinear systems with norm-bounded disturbances and parametric uncertainties while robustly satisfying con-straints. The proposed approach jointly optimizes a nominal nonlinear trajectory and an error feedback, requiring minimal offline design effort and offering low conservatism. This is achieved by decomposing the affine-in-the-parameter uncertain nonlinear system into a nominal nonlinear system and an uncertain linear time-varying system. Using this decomposition, we can apply established tools from system level synthesis to convexly over-bound all uncertainties in the nonlinear optimization problem. Moreover, it enables tight joint optimization of the linearization error bounds, parametric uncertainties bounds, nonlinear trajectory, and error feedback. With this novel controller parameterization, we can formulate a convex constraint to ensure robust performance guarantees for the non-linear system. The presented method is relevant for numerous applications related to trajectory optimization, e.g., in robotics and aerospace engineering. We demonstrate the performance of the approach and its low conservatism through the simulation example of a post-capture satellite stabilization.

10 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
RRRahel Rickenbach
Rahel Rickenbach
JTJelena Trisovic
Jelena Trisovic
ADAlexandre Didier
Alexandre Didier
JSJerome Sieber
Jerome Sieber
MZMelanie N. Zeilinger
Melanie N. Zeilinger
Although softmax attention drives state-of-the-art performance for sequence models, its quadratic complexity limits scalability, motivating linear alternatives such as state space models (SSMs). While these alternatives improve efficiency, their fundamental differences in information processing remain poorly understood. In this work, we leverage the recently proposed dynamical systems framework to represent softmax, norm and linear attention as dynamical systems, enabling a structured comparison with SSMs by analyzing their respective eigenvalue spectra. Since eigenvalues capture essential aspects of dynamical system behavior, we conduct an extensive empirical analysis across diverse sequence models and benchmarks. We first show that eigenvalues influence essential aspects of memory and long-range dependency modeling, revealing spectral signatures that align with task requirements. Building on these insights, we then investigate how architectural modifications in sequence models impact both eigenvalue spectra and task performance. This correspondence further strengthens the position of eigenvalue analysis as a principled metric for interpreting, understanding, and ultimately improving the capabilities of sequence models.

30 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
ADAlexandre Didier
Alexandre Didier
JSJerome Sieber
Jerome Sieber
MZMelanie N. Zeilinger
Melanie N. Zeilinger
We present an optimisation-based method for synthesising a dynamic regret optimal controller for linear systems with potentially adversarial disturbances and known or adversarial initial conditions. The dynamic regret is defined as the difference between the true incurred cost of the system and the cost which could have optimally been achieved under any input sequence having full knowledge of all future disturbances for a given disturbance energy. This problem formulation can be seen as an alternative to classical $\mathcal{H}_2$- or $\mathcal{H}_\infty$-control. The proposed controller synthesis is based on the system level parametrisation, which allows reformulating the dynamic regret problem as a semi-definite problem. This yields a new framework that allows to consider structured dynamic regret problems, which have not yet been considered in the literature. For known pointwise ellipsoidal bounds on the disturbance, we show that the dynamic regret bound can be improved compared to using only a bounded energy assumption and that the optimal dynamic regret bound differs by at most a factor of $\frac{2}{\pi}$ from the computed solution. Furthermore, the proposed framework allows guaranteeing state and input constraint satisfaction.