Talk of Dr Michael Muehlebach from Max Planck Institute for Intelligent Systems
Event details
| Date | 21.06.2024 |
| Hour | 11:15 › 12:15 |
| Speaker | Dr Michael Muehlebach from Max Planck Institute for Intelligent Systems |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Title: A Systems Theory for Algorithms: Perspectives from Learning, Control, and Optimization
Abstract: My talk discusses how systems theory can be used for analyzing and designing large-scale learning and optimization algorithms. The system-theoretic approach enables the analysis of nonconvex problems, unifies discrete-time and continuous-time models, and rigorously explains why structure-preserving (symplectic) discretization schemes are important. I will also use systems theory to design new algorithms for constrained optimization, and highlight numerous practical applications including the simulation of traffic networks, sparse regression, robust training of machine learning models, online regret minimization for cyber-physical systems, and the design of underactuated robotic systems.
Bio: Michael Muehlebach studied mechanical engineering at ETH Zurich and specialized in robotics, systems, and control during his Master's degree. He received the B.Sc. and the M.Sc. in 2010 and 2013, respectively, before joining the Institute for Dynamic Systems and Control for his Ph.D. He graduated under the supervision of Prof. R. D'Andrea in 2018 and joined the group of Prof. Michael I. Jordan at the University of California, Berkeley as a postdoctoral researcher. In 2021 he started as an independent group leader at the Max Planck Institute for Intelligent Systems in Tuebingen, where he leads the group "learning and dynamical systems".
He is interested in a variety of subjects, including machine learning, dynamical systems, and optimization. During his Ph.D. he developed approximations to the constrained linear quadratic regulator problem, a central problem in control theory, and applied these to model predictive control. He also designed control and estimation algorithms for balancing robots and flying machines. His more recent work straddles the boundary between machine learning and optimization, and includes the analysis of momentum-based and constrained optimization algorithms from a dynamical systems point of view.
He received the Outstanding D-MAVT Bachelor Award for his Bachelor's degree and the Willi-Studer prize for the best Master's degree. His Ph.D. thesis was awarded with the ETH Medal and the HILTI prize for innovative research. He was also awarded a Branco Weiss Fellowship and an Emmy Noether Fellowship, which fund his research group.
Abstract: My talk discusses how systems theory can be used for analyzing and designing large-scale learning and optimization algorithms. The system-theoretic approach enables the analysis of nonconvex problems, unifies discrete-time and continuous-time models, and rigorously explains why structure-preserving (symplectic) discretization schemes are important. I will also use systems theory to design new algorithms for constrained optimization, and highlight numerous practical applications including the simulation of traffic networks, sparse regression, robust training of machine learning models, online regret minimization for cyber-physical systems, and the design of underactuated robotic systems.
Bio: Michael Muehlebach studied mechanical engineering at ETH Zurich and specialized in robotics, systems, and control during his Master's degree. He received the B.Sc. and the M.Sc. in 2010 and 2013, respectively, before joining the Institute for Dynamic Systems and Control for his Ph.D. He graduated under the supervision of Prof. R. D'Andrea in 2018 and joined the group of Prof. Michael I. Jordan at the University of California, Berkeley as a postdoctoral researcher. In 2021 he started as an independent group leader at the Max Planck Institute for Intelligent Systems in Tuebingen, where he leads the group "learning and dynamical systems".
He is interested in a variety of subjects, including machine learning, dynamical systems, and optimization. During his Ph.D. he developed approximations to the constrained linear quadratic regulator problem, a central problem in control theory, and applied these to model predictive control. He also designed control and estimation algorithms for balancing robots and flying machines. His more recent work straddles the boundary between machine learning and optimization, and includes the analysis of momentum-based and constrained optimization algorithms from a dynamical systems point of view.
He received the Outstanding D-MAVT Bachelor Award for his Bachelor's degree and the Willi-Studer prize for the best Master's degree. His Ph.D. thesis was awarded with the ETH Medal and the HILTI prize for innovative research. He was also awarded a Branco Weiss Fellowship and an Emmy Noether Fellowship, which fund his research group.
Practical information
- Informed public
- Free
Organizer
- Professor Volkan Cevher
Contact
- Gosia Baltaian