Sample Complexity for Discrete System Identification
Event details
| Date | 21.02.2025 |
| Hour | 11:00 › 12:00 |
| Speaker | Professor Carolyn Beck, Arthur Davis Faculty Scholar Associate Head for Undergraduate Programs ISE Department Grainger College of Engineering University of Illinois (USA) Urbana-Champaign |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract:
Classic system identification methods focus on identifying continuous-valued dynamical systems from input-output data, where the main analysis of such approaches largely focuses on asymptotic convergence of the estimated models to the true models, i.e., consistency properties. More recent identification approaches have focused on sample complexity properties, i.e., how much data is needed to achieve an acceptable model approximation. In this talk we will give a brief overview of classical methods and then discuss more recent data-driven methods for modeling both continuous-valued linear systems and discrete-valued dynamical systems evolving over networks. Examples of the latter include the spread of viruses and diseases over human contact networks, the propagation of ideas and misinformation over social networks, and the spread of financial default risk between banking and economic institutions. In many of these systems, data may be widely available, but approaches to identify relevant mathematical models, including underlying network topologies, are not widely established or agreed upon. We will discuss the problem of modeling discrete-valued, discrete-time dynamical systems evolving over networks, and outline analysis results under maximum likelihood identification approaches that guarantee consistency conditions and sample complexity bounds. Applications to the aforementioned examples will be further discussed as time allows.
Biography:
Professor Carolyn Beck received her PhD from California Institute of Technology (Caltech), her MS from Carnegie Mellon, and her BS from California State Polytechnic University, all in Electrical Engineering. Prior to her PhD studies, she worked as a Research and Development Engineer for Hewlett-Packard in silicon valley.
She is currently Associate Head and Professor at the University of Illinois at Urbana-Champaign in Industrial and Systems Engineering, and has held visiting positions at KTH (Stockholm, Sweden), Stanford University and Lund University (Sweden). She is the President of the IEEE Control Systems Society (CSS) and serves on it's Board of Governors, and is the General Chair for the 2025 American Control Conference to be held in July in Denver, Colorado. She has served as an Associate Editor for the IEEE Transactions on Automatic Control, the IEEE Transactions on Control of Network Systems, the IEEE CSS Conference Editorial Board, and on the IPC of numerous international conferences.
Carolyn is an IEEE Fellow and an IEEE CSS Distinguished Lecturer. She has been the recipient of a National Science Foundation CAREER Award, an Office of Naval Research Young Investigator Award, and teaching awards at the University of Illinois. Her primary research interests lie in the development of model approximation methods, network inference and aggregation, and distributed optimization and control, with applications to spread process dynamics, and water and energy networks.
Practical information
- General public
- Free
Organizer
- Professor Alireza Karimi
Contact
- barbara.schenkel@epfl.ch