Talk Information 12/05/2024

Abstract: The rapid advancements in large AI models have underscored the importance of scaling laws, which demonstrate that model capability increases with larger architectures and richer datasets. However, these advancements pose dual challenges: i) on the learning front, ensuring that in addition to accuracy, new evaluation metrics – such as fairness, safety, and robustness – are met; ii) on the computing front, meeting stringent demands for efficient sensing, communication, and processing. Addressing these challenges necessitates principled methods to handle multiple (possibly competing) performance metrics and resource constraints. In this talk, I will introduce a unified framework to tackle these challenges in learning and computing problems, grounded in bilevel optimization. This framework provides theoretical guarantees on optimality, complexity, as well as algorithmic scalability for large-scale AI models and systems. I will conclude by showcasing applications of bilevel optimization techniques in NextG wireless problems and IBM’s signal processing systems.

Bio: Tianyi Chen is an Assistant Professor in the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute (RPI), where he is jointly supported by the RPI – IBM Artificial Intelligence Research Partnership. Before joining RPI at 2019, Dr. Chen received his B. Eng. degree from Fudan University in 2014, and the Ph.D. degree from the University of Minnesota in 2019. Dr. Chen’s research centers on the foundations of bilevel and multi-objective optimization and learning, with a focus on their applications to emerging computing paradigms such as wireless computing, and analog computing systems. His work bridges theory and practice, addressing critical challenges in computing and AI, and resulting in patents and contributions to several IBM’s industrial products.
Dr. Chen is the inaugural recipient of IEEE Signal Processing Society Best PhD Dissertation Award in 2020, a recipient of NSF CAREER Award in 2021, and several industrial research awards including Amazon Research Award and Cisco Research Award. He is also the co-author of several best (student) paper awards including one at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).