About Me

Hi, I am currently a Postdoctoral Associate at MIT’s Laboratory for Information and Decision Systems (LIDS), mentored by Prof. Cathy Wu. Previously, I was a Research Fellow at Nanyang Technological University (NTU), collaborating with Prof. Jie Zhang and Prof. Zhiguang Cao (from SMU). I obtained my Ph.D. degree in Industrial Systems Engineering at National University of Singapore (NUS), in March 2024, where I am honored to be advised by Prof. Yeow Meng Chee. I received my B.E. degree from School of Computer Science and Engineering, South China University of Technology (SCUT), in June 2019, advised by Prof. Yuejiao Gong.

I am working at the intersection of Machine Learning (ML) and Optimization, striving to develop automated ML solutions to address complex optimization and decision-making challenges. My research has been featured in top-tier conferences such as ICML, NeurIPS, ICLR, KDD, etc, and top-tier journals such as TPAMI, TNNLS, SMCA, TITS, etc. I have served as an Area Chair for the IEEE CAI conference and actively served as a Reviewer/PC Member for top-tier conferences, workshops, and journals, recognized with best reviewer awards.

Welcome to see my publications, academic services, experience, and honors & awards, and welcome to reach out for collaboration! You may approach me at:

  • Office: 45-611, 51 Vassar St, Cambridge, MA 02139
  • E-mail: yiningma [at] mit [dot] edu

💡 Research Interests

My research has primarily focused on the emerging field of “Learning to Optimize (L2Opt)”, where the latest ML techniques (e.g., reinforcement learning, deep learning, large language models, etc) are exploited to develop state-of-the-art ML-powered frameworks/approaches for addressing challenging real-world optimization problems (e.g., combinatorial optimization, black-box optimization, mixed integer linear programming, etc). My research in L2Opt spans various ML perspectives, such as representation learning, foundation model development, efficient training/inference framework design, out-of-distribution generalization, multi-agent coordination, decision-making in dynamic environments, etc.

Research Keywords

  • Machine Learning: Reinforcement Learning, Deep Learning, Large Language Model (LLM), Federated/Distributed Learning, Multi-Agent Systems
  • Optimization: Combinatorial Optimization, MILP, Black-Box Optimization
  • Application: Routing, Planning, Logistics, Transportation, Autonomous Vehicles

🎉 News

  • [12/2024] ✈️ I will be attending NeurIPS’24 in person. See you in Vancouver, Canada! 🇨🇦
  • [11/2024] One paper on L2Opt got accepted by KDD’25, where we proposed a neural approach for optimizing diverse, high-quality solutions to Multi-Solution TSP (MSTSP).
  • [10/2024] I am selected as NeurIPS 2024 Top Reviewer (10%) for both main and DB track!
  • [09/2024] One paper on L2Opt got accepted by NeurIPS’24, where we propose Proactive Infeasibility Prevention (PIP) to elevate neural solvers for complex VRP constraints.
  • [08/2024] One paper on L2Opt got accepted by TPAMI, where we promoted a neural collaborative framework integrating learning-to-search and learning-to-construct solvers.
  • [08/2024] I’m so excited to join Prof. Cathy Wu’s group in MIT!
  • [07/2024] I am selected as ICML 2024 Best Reviewer (< 3%)!
  • [06/2024] Check out RL4CO - our latest extensive benchmark to unify frameworks and facilitate research in RL-based CO algorithms 🚀.
  • [05/2024] One paper on L2Opt got accepted by KDD’24, where we proposed a hierarchical neural solver for realistic TSPs under real-world customer distributions.
  • [05/2024] One paper on L2Opt got accepted by ICML’24, where we introduced MVMoE, a step towards multi-task domain foundation models for VRPs based on mixture of experts.
  • [05/2024] Promoted to the Research Fellow in NTU.
  • [03/2024] One paper on MARL got accepted by TNNLS, where we introduced DOMAC for opponent modelling in multi-agent systems using only local information.
  • [03/2024] One paper on L2Opt got accepted by SMCA, where we introduced RL-DAS for dynamic algorithm selection based on deep reinforcement learning.
  • [02/2024] Gave a talk at MIT, hosted by Prof. Cathy Wu.
  • [02/2024] Successfully defended my PhD thesis at NUS 🎓!



Flag Counter