Ming Yan

Ming Yan is an Associate Professor and Assistant Dean at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), where he has been serving since 2022. Prior to this position, he was an Associate Professor at Michigan State University from 2021 to 2023 (on leave from 2022 to 2023) and an Assistant Professor from 2015 to 2021. His academic journey includes postdoctoral positions at UCLA and Rice University.

His educational background includes:

• Ph.D. in Mathematics from University of California, Los Angeles (UCLA), 2012
• M.S. in Mathematics from University of Science and Technology of China (USTC), 2008
• B.S. in Mathematics from University of Science and Technology of China (USTC), 2005

Ming Yan's research focuses on optimization methods, particularly for sparse recovery and inverse problems. His work extends to federated and machine learning algorithms, parallel and distributed algorithms for large-scale data, and variational techniques in image processing. His approach often combines theoretical analysis with practical applications, developing algorithms that address computational challenges in modern data science.

His recent publications demonstrate a strong focus on decentralized optimization, primal-dual algorithms, and sparse recovery techniques. These works span theoretical developments in convergence analysis and practical applications in machine learning and signal processing. His research has evolved from foundational work in image processing to more recent contributions in distributed learning and federated systems, reflecting the changing landscape of data science.

Ming Yan is actively involved in mentoring students and has indicated that he is recruiting Ph.D. students, postdocs, and visiting students at CUHK-Shenzhen. His teaching portfolio includes courses in calculus, optimization, and computational methods across multiple institutions.

His research is supported by various grants, though specific details are not provided in the available information. He has developed several algorithms and software implementations, including the PD3O framework for convex optimization algorithms.