Dr. YUAN Yancheng

YUAN Yancheng

I am an Assistant Professor in the Department of Applied Mathematics at The Hong Kong Polytechnic University.

I also serve as an Assistant Director of the Research Center for Intelligent Operations Research and an Associate Director of the CITIC-PolyU Interdisciplinary Mathematical Digital AI Joint Laboratory. Previously, I was a research fellow at NUS NExT Center working with Prof. Tat-Seng CHUA.

Education

Ph.D. Math. National University of Singapore 2015 – 2020
B.S. Comp. Math. University of Science and Technology of China 2011 – 2015
Supervisor: Prof. Juyong Zhang

Research Interests

  • Optimization Algorithm design, analysis, and solver development.
  • Artificial Intelligence (AI) Foundation models and mathematical foundations for data science.
  • Data-driven Applications Recommendation systems and healthcare analytics.

Selected Recent Publications

View All

Magnitude-modulated equivariant adapter for parameter-efficient fine-tuning of equivariant graph neural networks

Dian Jin, Yancheng Yuan, and Xiao-Ming Tao

The 40th Annual AAAI Conference on Artificial Intelligence, 2026 (AAAI '26).

HPR-LP: An implementation of an HPR method for solving linear programming

Kaihuang Chen, Defeng Sun, Yancheng Yuan, Guojun Zhang, and Xinyuan Zhao

Mathematical Programming Computation, 2025.

Randomly projected convex clustering model: Motivation, realization, and cluster recovery guarantees

Ziwen Wang, Yancheng Yuan, Jiaming Ma, Tieyong Zeng, and Defeng Sun

Journal of Machine Learning Research, 26(137):1−57, 2025.

LAMBDA: A large model based data agent

Maojun Sun , Ruijian Han , Binyan Jiang , Houduo Qi , Defeng Sun, Yancheng Yuan, and Jian Huang

Journal of the American Statistical Association, 2025.
Selected as a discussion paper!

HOT: An efficient Halpern accelerating algorithm for optimal transport problems

Guojun Zhang, Zhexuan Gu, Yancheng Yuan, and Defeng Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47: 6703--6714, 2025.

Adaptive sieving: A dimension reduction technique for sparse optimization problems

Yancheng Yuan, Meixia Lin, Defeng Sun, and Kim-Chuan Toh

Mathematical Programming Computation, 17: 585--616, 2025.

Accelerating preconditioned ADMM via degenerate proximal point mappings

Defeng Sun, Yancheng Yuan, Guojun Zhang, and Xinyuan Zhao

SIAM Journal on Optimization, 35: 2 1165--1193, 2025.

Selected Open-source Software

HPR-LP

HPR-LP

Solver

A GPU-accelerated solver for large-scale linear programming.

Julia / C / CUDA GitHub →
HPR-QP

HPR-QP

Solver

A GPU-accelerated solver for large-scale convex composite quadratic programming.

Julia / CUDA GitHub →
HOT

HOT

Optimal Transport

A GPU-accelerated solver designed specifically for large-scale 2D optimal transport problems.

Python / CUDA GitHub →
Convex Clustering

Convex Clustering

Efficient solvers for generating high-quality solutions to the convex clustering model path.

Python / MATLAB Python→MATLAB →
Adaptive Sieving

Adaptive Sieving

A MATLAB software designed to use adaptive sieving (a dimension reduction technique) for sparse optimization problems.

MATLAB GitHub →
LAMBDA

LAMBDA

LLM Agent

A coding-free multi-agent data analysis system leveraging the power of large language models.

Python GitHub →