The continuously increasing interest in intelligent autonomous systems underlines the need for new developments in cyber-physical systems that can learn, adapt, and reason. Towards this direction, we will formally analyze the properties of learning for inference and control in cyber-physical systems, where time and computational resources are limited, and robustness and interpretability are prioritized. We will focus on the notion of progressive learning: an adaptive process that hierarchically approximates the solution of an optimal decision-making problem given real-time observations of a system and its environment. We will introduce the Online Deterministic Annealing (ODA) approach as a gradient-free stochastic optimization method to construct a learning model that progressively increases its complexity as needed, through an intuitive bifurcation phenomenon. We will study the properties of robustness and interpretability, and the importance of being able to control the performance-complexity trade-off in real time. Finally, we will discuss how these properties can be incorporated in the development of system identification and robust reinforcement learning algorithms with applications in robotics and multi-agent systems.
Christos Mavridis received his Ph.D. in electrical and computer engineering at the University of Maryland, College Park in 2021. His research interests include systems and control theory, stochastic optimization, learning theory, multi-agent systems, and robotics. He is currently a postdoctoral research associate at the University of Maryland and has served as a visiting postdoc fellow at KTH Royal Institute of Technology. He has also worked as a researcher for the Math and Algorithms Research Group at Nokia Bell Labs, NJ and the System Sciences Lab at Xerox Palo Alto Research Center (PARC), CA. Dr. Mavridis has received several fellowships and awards, including the Ann G. Wylie Dissertation Fellowship in 2021. He has been a finalist in the Qualcomm Innovation Fellowship US in 2018, and has received the Best Student Paper Award (1st place) in the IEEE International Conference on Intelligent Transportation Systems (ITSC), 2021.