Assistant Professor Jian Li from the Department of Applied Mathematics and Statistics and the Department of Computer Science has earned a U.S. National Science Foundation (NSF) Early CAREER award for his project, “CAREER: Structured Learning and Optimization for Efficient Management in the Wireless Edge Cloud: Theory and Algorithms.”
A variety of resource-intensive distributed computing loads in the context of machine learning model training and streaming data analysis with applications such as smart city, swarm coordination, and telemedicine have emerged in recent years. These compute loads often consist of graph-based jobs with computation task nodes and communication-based edges with dependencies between these tasks.
“Due to high communication costs or privacy concerns, a graph-based job is preferred to perform distributively at the wireless edge cloud,” said Li. “To achieve this, the computation tasks of a job that require computation and communication resources must be mapped to physical servers in the wireless edge cloud.”
Most existing wireless network scheduling algorithms rarely account for logical relationships between computation tasks of a graph-based job, and most existing learning algorithms pay little attention to the underlying wireless network constraints. “Their successes in practice are further impeded due to the curse-of-dimensionality and lack of expressiveness and adaptation. This project aims to bridge the gap between prevailing graph-based job services and wireless edge cloud designs via advocating structured learning and optimization solutions with provable performance guarantees,” said Li. “The results will enhance the performance of wireless edge networks for distributed computing loads. At the same time this project develops fundamental theories that pertain to the area of machine learning, especially reinforcement learning and distributed learning.”
“These awards are extremely competitive and are selectively given to the nation’s most promising researchers. We are very proud of Jian,” said Professor Joe Mitchell, chair of the Department of Applied Mathematics and Statistics. “Professor Li’s project seeks to improve our fundamental understanding in areas of reinforcement learning, optimization, and scheduling, with potential broader impacts on the performance and responsiveness of edge and cloud computing, which is a core technology we all rely upon, especially for the ever-expanding suite of AI tools that have become an integral part of our daily lives.”
Li earned his doctorate in computer engineering from Texas A&M University in 2016 and his bachelor of engineering from Shanghai Jiao Tong University in 2012. He was a postdoc with the College of Information and Computer Sciences at University Massachusetts Amherst from 2017 to 2019 before joining Stony Brook University as an assistant professor in 2023.
His research focuses on reinforcement learning and multi-armed bandits, federated/decentralized learning, and their applications in next-generation networked systems (e.g., wireless networks, edge, and cloud computing).
NSF CAREER Awards support early-career faculty who have the potential to serve as academic role models in research education while leading advances within their departments or organizations. Activities pursued by early-career faculty should build a firm foundation for a lifetime leadership integrating education research. It is among NSF’s most prestigious national honors major milestone university faculty.