February 23, 2023 Thursday
Abstract:
The integration of AI techniques into real-world physical systems has garnered significant interest in recent years, with the promise of providing new data-driven solutions to real-world problems. However, this integration also poses practical issues such as reliability, scalability, and trustworthiness for AI-integrated algorithms. In this talk, we will present a framework that strikes a balance between the robustness and consistency tradeoff when designing online algorithms with machine learning predictions, and discuss its limitations. Using discrete control models, we will demonstrate potential solutions and their applications in smart grids. Finally, we will explore intriguing research directions for future work in this rapidly evolving field. The goal of this introductory talk is to shed light on the challenges and opportunities of AI integration into real-world cyber-physical systems and inspire further research in this area.
Speaker Bio:
Dr. Tongxin Li
Tenure-track Assistant Professor, School of Data Science (SDS), CUHK-Shenzhen
Tongxin Li is currently a tenure-track assistant professor in the School of Data Science (SDS) at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen).Prior to joining SDS, he received his PhD in CMS at the California Institute of Technology, and he graduated from CUHK in a dual-degree program and obtained a BEng in information engineering, a BSc in mathematics and an MPhil in information engineering. His research interests focus on interdisciplinary topics in machine learning, control, and optimization, and he is interested in developing trustworthy machine learning techniques.