Ming Yuan | Model Compression Award | Best Researcher Award

Mr Ming Yuan | Model Compression Award | Best Researcher Award

Mr Ming Yuan, City University of Hong Kong , Hong Kong

Ming Yuan is a distinguished scholar in the field of applied mathematics, currently pursuing a Master of Applied Mathematics at Northwestern Polytechnical University (2021-2024). He holds a Bachelor of Science in Statistics from Shandong University (2015-2019). Yuan has made significant contributions to the areas of nonlinear dynamical systems, model compression, and optimization. His research has been published in prestigious journals such as Neurocomputing and Discrete Applied Mathematics. Notable works include a systematic DNN weight pruning framework and studies on the α-index of minimally connected graphs. Yuan has received several accolades, including the 2024 Outstanding Master’s Graduate Award and multiple scholarships. His work reflects a blend of theoretical innovation and practical application, positioning him as a promising researcher in his field.

Publication Profile

Scopus

Education

Ming Yuan is currently completing his Master of Applied Mathematics at Northwestern Polytechnical University, a program he commenced in September 2021 and is set to finish in April 2024. Prior to this, Yuan earned his Bachelor of Science in Statistics from Shandong University, China, where he studied from September 2015 to June 2019. During his undergraduate studies, he developed a strong foundation in statistical theories and methodologies, which has been instrumental in his advanced research. Yuan’s academic journey is marked by a commitment to excellence and a passion for exploring complex mathematical concepts. His educational background has provided him with the skills and knowledge necessary to contribute significantly to the field of applied mathematics, particularly in nonlinear dynamical systems, model compression, and optimization.

Experience 

Ming Yuan has accumulated substantial experience in mathematical research and academia. As a Master’s student at Northwestern Polytechnical University, he has been deeply involved in various research projects since September 2021. Yuan’s work primarily focuses on nonlinear dynamical systems, model compression, and optimization, areas in which he has published extensively. His notable publications include a systematic DNN weight pruning framework based on symmetric accelerated stochastic ADMM and studies on the α-index of minimally connected graphs. Additionally, Yuan has collaborated with renowned researchers, contributing to high-impact journals like Neurocomputing and Discrete Applied Mathematics. His practical experience is further enriched by his undergraduate tenure at Shandong University, where he engaged in several scientific research projects and mathematical contests. This blend of rigorous academic training and hands-on research experience positions Yuan as a capable and innovative researcher in his field.

Research Focus 

Ming Yuan’s research focuses on several critical areas within applied mathematics, including nonlinear dynamical systems, model compression, and optimization. His work aims to develop innovative solutions and methodologies that address complex mathematical problems. One of his key contributions is a systematic DNN weight pruning framework based on symmetric accelerated stochastic ADMM, which has been published in Neurocomputing. Additionally, Yuan has explored the α-index of minimally connected graphs, contributing to the field of graph theory. His research is characterized by a rigorous analytical approach and a commitment to advancing theoretical understanding while ensuring practical applicability. Yuan’s studies often involve interdisciplinary collaboration, enhancing the impact and relevance of his findings. His dedication to exploring new frontiers in mathematics positions him as a forward-thinking researcher with a promising future in academia and beyond.

Publication Top Notes

A systematic DNN weight pruning framework based on symmetric accelerated stochastic ADMM

On the α-index of minimally 2-connected graphs with given order or size