Dr. Zecchin Matteo - Postdoctoral Research Associate at the King's Communications, Learning & Information Processing lab at King’s College London Communication systems
Date: - Location: Eurecom
Abstract: In the context of cyber-physical systems, ensuring reliability and safety in predictive control is challenging due to inherent prediction uncertainty. In this talk, we present Probabilistic Time Series-Conformal Risk Prediction (PTS-CRC), a novel method for improving prediction reliability. PTS-CRC generates predictive sets that efficiently handle uncertainties in complex dynamic environments, going beyond traditional coverage-based approaches. PTS-CRC also allows for the development of a Model Predictive Control framework that caters to open-loop and closed-loop control problems while satisfying quality and safety constraints. We conclude the talk by illustrating how the proposed framework can be leveraged in wireless networking to reliably monitor the wireless channel evolution and derive safe power control policies subject to maximum interference constraints and minimal decoding packet probability guarantees. Bio: Dr. Zecchin Matteo is a Postdoctoral Research Associate at the King's Communications, Learning & Information Processing lab at King’s College London. He obtained his PhD in Telecommunication Engineering from EURECOM in 2022. His research focuses on the intersection of wireless communication and machine learning, with a particular emphasis on the application of Bayesian methods to wireless communication systems and decentralized learning approaches.
