Intelligent Systems



no image
Deep Backtracking Counterfactuals for Causally Compliant Explanations

Kladny, K., Kügelgen, J. V., Schölkopf, B., Muehlebach, M.

Transactions on Machine Learning Research, July 2024 (article)

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


no image
Balancing a 3D Inverted Pendulum using Remote Magnetic Manipulation

Zughaibi, J., Nelson, B. J., Muehlebach, M.

Robotics and Automation Letters, 2024 (article) In revision

link (url) [BibTex]

link (url) [BibTex]


no image
Conformal Performance Range Prediction for Segmentation Output Quality Control

Wundram, A., Fischer, P., Muehlebach, M., Koch, L., Baumgartner, C.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024 (conference) Submitted

[BibTex]

[BibTex]


no image
Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy

Fischer, P., Willms, H., Muehlebach, M., Thorwarth, D., Schneider, M., Baumgartner, C.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024 (conference)

[BibTex]

[BibTex]


no image
Towards a systems theory of algorithms

Florian Dörfler, Zhiyu He, Giuseppe Belgioioso, Saverio Bolognani, John Lygeros, Michael Muehlebach

IEEE Control System Letters, 2024 (article)

link (url) [BibTex]

link (url) [BibTex]


no image
Online learning under adversarial nonlinear constraints

Kolev, P., Martius, G., Muehlebach, M.

In Advances in Neural Information Processing Systems 36, 2024 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
A Pontryagin Perspective on Reinforcement Learning

Eberhard, O., Vernade, C., Muehlebach, M.

Max Planck Institute for Intelligent Systems, 2024 (techreport)

link (url) [BibTex]

link (url) [BibTex]


no image
Distributed Event-Based Learning via ADMM

Er, D., Trimpe, S., Muehlebach, M.

Max Planck Institute for Intelligent Systems, 2024 (techreport)

link (url) [BibTex]

link (url) [BibTex]


no image
Gray-box nonlinear feedback optimization

He, Z., Bolognani, S., Muehlebach, M., Dörfler, F.

IEEE Transactions on Automatic Control, 2024 (article) Submitted

link (url) [BibTex]

link (url) [BibTex]


no image
Accelerated First-Order Optimization under Nonlinear Constraints

Muehlebach, M., Jordan, M. I.

Mathematical Programming, 2024 (article) Submitted

link (url) [BibTex]

link (url) [BibTex]


no image
Primal Methods for Variational Inequality Problems with Functional Constraints

Zhang, L., He, N., Muehlebach, M.

Mathematical Programming, 2024 (article) Submitted

link (url) [BibTex]

link (url) [BibTex]

2023


no image

no image
Causal Effect Estimation from Observational and Interventional Data Through Matrix Weighted Linear Estimators

Kladny, K., von Kügelgen, J., Schölkopf, B., Muehlebach, M.

Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI), 216, pages: 1087-1097, Proceedings of Machine Learning Research, (Editors: Evans, Robin J. and Shpitser, Ilya), PMLR, August 2023 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Black-Box vs. Gray-Box: A Case Study on Learning Table Tennis Ball Trajectory Prediction with Spin and Impacts

Achterhold, J., Tobuschat, P., Ma, H., Büchler, D., Muehlebach, M., Stueckler, J.

In Proceedings of the 5th Annual Learning for Dynamics and Control Conference (L4DC), 211, pages: 878-890, Proceedings of Machine Learning Research, (Editors: Nikolai Matni, Manfred Morari and George J. Pappa), PMLR, June 2023 (inproceedings)

preprint code link (url) [BibTex]

preprint code link (url) [BibTex]


no image
CausalEffect Estimation by Combining Observational and Interventional Data

Kladny, K.

ETH Zurich, Switzerland, February 2023 (mastersthesis)

[BibTex]


no image
A Dynamical Systems Perspective on Discrete Optimization

Tong, G., Muehlebach, M.

Conference on Learning for Dynamics and Control, 2023 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Data-Efficient Online Learning of Ball Placement in Robot Table Tennis

Tobuschat, P., Ma, H., Büchler, D., Schölkopf, B., Muehlebach, M.

EEE/RSJ International Conference on Intelligent Robots and Systems, 2023 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Orthogonal Directions Constrained Gradient Method: from Non-Linear Equality Constraints to Stiefel Manifold

Schechtman, S., Tiapkin, D., Muehlebach, M., Moulines, E.

Conference on Learning Theory, 2023 (conference)

link (url) [BibTex]

link (url) [BibTex]

2022


no image
Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization

Das, A., Schölkopf, B., Muehlebach, M.

Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pages: 6749-6762, (Editors: S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh), Curran Associates, Inc., 36th Conference on Neural Information Processing Systems (NeurIPS 2022) , December 2022 (conference)

arXiv link (url) [BibTex]

2022

arXiv link (url) [BibTex]


no image
A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles

Ma, H., Büchler, D., Schölkopf, B., Muehlebach, M.

Proceedings of Robotics: Science and Systems XVIII (R:SS 2022), 18, (Editors: Kris Hauser, Dylan Shell, and Shoudong Huang), Robotics: Science and Systems XVIII, June 2022 (conference)

PDF link (url) DOI [BibTex]

PDF link (url) DOI [BibTex]


no image
On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems

Muehlebach, M., Jordan, M. I.

Journal of Machine Learning Research, 23, 2022 (article)

Abstract
We introduce a class of first-order methods for smooth constrained optimization that are based on an analogy to non-smooth dynamical systems. Two distinctive features of our approach are that (i) projections or optimizations over the entire feasible set are avoided, in stark contrast to projected gradient methods or the Frank-Wolfe method, and (ii) iterates are allowed to become infeasible, which differs from active set or feasible direction methods, where the descent motion stops as soon as a new constraint is encountered. The resulting algorithmic procedure is simple to implement even when constraints are nonlinear, and is suitable for large-scale constrained optimization problems in which the feasible set fails to have a simple structure. The key underlying idea is that constraints are expressed in terms of velocities instead of positions, which has the algorithmic consequence that optimizations over feasible sets at each iteration are replaced with optimizations over local, sparse convex approximations. The result is a simplified suite of algorithms and an expanded range of possible applications in machine learning.

link (url) [BibTex]


no image
First-order Constrained Optimization: Non-smooth Dynamical System Viewpoint

Schechtman, S., Tiapkin, D., Moulines, E., Muehlebach, M.

IFAC Workshop on Control Applications of Optimization, 2022 (conference)

link (url) [BibTex]

link (url) [BibTex]

2021


no image
Optimization with Adaptive Step Size Selection from a Dynamical Systems Perspective

Wadia, N. S., Jordan, M. I., Muehlebach, M.

OPT2021 Workshop, Conference on Neural Information Processing Systems, Thirty-fifth Conference on Neural Information Processing Systems, 2021 (conference)

link (url) [BibTex]

2021

link (url) [BibTex]

2015


no image
LMI-Based Synthesis for Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceedings of the American Control Conference, July 2015 (inproceedings)

Abstract
This paper presents an LMI-based synthesis procedure for distributed event-based state estimation. Multiple agents observe and control a dynamic process by sporadically exchanging data over a broadcast network according to an event-based protocol. In previous work [1], the synthesis of event-based state estimators is based on a centralized design. In that case three different types of communication are required: event-based communication of measurements, periodic reset of all estimates to their joint average, and communication of inputs. The proposed synthesis problem eliminates the communication of inputs as well as the periodic resets (under favorable circumstances) by accounting explicitly for the distributed structure of the control system.

PDF DOI Project Page [BibTex]

2015

PDF DOI Project Page [BibTex]


no image
Guaranteed H2 Performance in Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]