Akang Wang

Operations Research

prof_pic.png

Hello, I’m Akang Wang, a Research Scientist at Shenzhen Research Institute of Big Data and an Adjunct Assistant Professor at CUHK-Shenzhen’s School of Data Science. I received my PhD in Process Systems Engineering from Carnegie Mellon University in 2020. My current research focuses on integer programming, learning to optimize, and grid optimization. My research is supported by National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen Science and Technology Program, and National Key R&D Program of China. I have published journal/conference papers in EJOR, ICLR, ICML, NeurIPS, etc. I won the first place in the primal track of NeurIPS 2021 ML2CO competition and the second place in the 2022 RAS Problem Solving Competition of INFORMS. Besides, I serve as reviewers for NeurIPS/ICLR/MPC etc.

In this website, you can know more about my research and experience. Also, please feel free to check out my Google Scholar and LinkedIn.

news

Jul 22, 2025 Our paper entitled “Solving Quadratic Programs via Deep Unrolled Douglas-Rachford Splitting” is accepted by TMLR.
May 01, 2025 Our paper entitled “ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-k-Cut Problems” is accepted by ICML 2025.
Apr 05, 2025 Our paper entitled “Mixed-Integer Linear Optimization via Learning-Based Two-Layer Large Neighborhood Search” is accepted by LION 2025.
Jan 23, 2025 Our paper entitled “When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach” is accepted by ICLR 2025.
Dec 15, 2024 Happy to be selected as “Top Reviewer of 2024 NeurIPS (Top 10%)”.
Oct 23, 2024 Our paper entitled “A Novel Mixed-Integer Linear Programming Formulation for Continuous-Time Inventory Routing” is accepted by Computers & Operations Research.
Sep 27, 2024 Our papers entitled “IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs” and “SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization” are accepted by NeurIPS 2024.
May 01, 2024 Our paper entitled “PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming” is accepted by ICML 2024.

latest posts