MechE Seminar: A Systems Theoretic Perspective on Algorithms

Thumbnail

Event details

Date 12.02.2025
Hour 09:0010:00
Speaker Dr. Michael Muehlebach, Learning and Dynamical Systems Group, Max Planck Institute for Intelligent Systems
Location Online
Category Conferences - Seminars
Event Language English
Abstract: Modern society relies on large-scale infrastructure systems, such as supply chains, transportation networks, and the electric grid - engineering marvels established over the last century. While the physical infrastructure is in place, we now face a critical challenge: creating algorithms that make these systems adaptive, resource-efficient, and resilient to disruptions.

My talk explores a systems theoretic perspective on algorithms, which provides a fresh viewpoint on these pressing needs. I will highlight foundational work on accelerated optimization, a cornerstone in modern optimization, showing how this perspective pinpoints the key principles behind accelerated convergence rates. I will also demonstrate how a system-theoretic lens facilitates the design of new algorithms for large-scale constrained optimization, and discuss practical applications including the simulation of traffic networks, sparse regression, robust training of machine learning models, constraint-aware sampling with diffusion models, and the design of underactuated robotic systems. These examples illustrate the potential of rethinking algorithms as dynamic, interacting components within complex systems.

Biography: 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, an Emmy Noether Fellowship, and an Amazon PhD Fellowship, which fund his research group.

Practical information

  • General public
  • Free

Tags

MechE Seminar: A Systems Theoretic Perspective on Algorithms

Share