Xinshang Wang

I work at Alibaba Group US, where I lead a team that builds core optimization software in C++, along with distributed algorithms and the surrounding platform. Some of us also pursue academic research. Previously, I was a postdoctoral associate at MIT’s Institute for Data, Systems, and Society. In 2017, I obtained my Ph.D. in Operations Research from Columbia University.

Research Interests

Optimization Software, Revenue Management, Supply Chain Management
Online Algorithms, Stochastic Optimization, Machine Learning for Optimization

Publications

• Simultaneous Confidence Bounds for Aggregated Effects via Exact Subset Optimization.
  Weihang Xu, Huajie Qian, Wotao Yin, and Xinshang Wang.
  International Conference on Machine Learning (ICML), 2026.
• Draft-and-Audit Reinforcement Learning for Optimization Modeling.
  Zeping Min, Weihang Xu, Zhengzhong You, Wotao Yin, and Xinshang Wang.
  International Conference on Machine Learning (ICML), 2026.
• ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research.
  Ruicheng Ao, David Simchi-Levi, and Xinshang Wang.
  International Conference on Machine Learning (ICML), 2026.
• Two-Stage Learning to Branch in Branch-Price-and-Cut Algorithms for Solving Vehicle Routing Problems Exactly.
  Zhengzhong You, Yu Yang, Xinshang Wang, and Wotao Yin.
  Operations Research, 74(4):1811–1833, 2026.
• ResiliBench: Evaluating Agentic Workflow Adaptation in Stochastic Environments.
  Ruicheng Ao, Zeping Min, Tingyu Zhu, Wotao Yin, and Xinshang Wang.
  International Conference on Learning Representations (ICLR), 91062–91103, 2026.
• Multi-item Online Order Fulfillment in a Two-Layer Network.
  Yanyang Zhao, Xinshang Wang, and Linwei Xin.
  Operations Research, 73(5):2297–2305, 2025.
• Technical Note—Online Matching with Bayesian Rewards.
  David Simchi-Levi, Rui Sun, and Xinshang Wang.
  Operations Research, 73(1):278–289, 2025.
• Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs.
  Ziang Chen, Xiaohan Chen, Jialin Liu, Xinshang Wang, and Wotao Yin.
  International Conference on Machine Learning (ICML), PMLR 267:7880–7911, 2025.
• DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models.
  Zeping Min and Xinshang Wang.
  International Conference on Learning Representations (ICLR), 65112–65142, 2025.
• DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee.
  Haoyu Wang, Jialin Liu, Xiaohan Chen, Xinshang Wang, Pan Li, and Wotao Yin.
  Transactions on Machine Learning Research, 2024.
• Rethinking the Capacity of Graph Neural Networks for Branching Strategy.
  Ziang Chen, Jialin Liu, Xiaohan Chen, Xinshang Wang, and Wotao Yin.
  Advances in Neural Information Processing Systems (NeurIPS), 37:123991–124024, 2024.
• Efficient Algorithms for Sum-of-Minimum Optimization.
  Lisang Ding, Ziang Chen, Xinshang Wang, and Wotao Yin.
  International Conference on Machine Learning (ICML), PMLR 235:10927–10959, 2024.
• HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent.
  Ziang Chen, Jianfeng Lu, Huajie Qian, Xinshang Wang, and Wotao Yin.
  International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 206:10732–10781, 2023.
• On Representing Linear Programs by Graph Neural Networks.
  Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, and Wotao Yin.
  International Conference on Learning Representations (ICLR), 2023.
• On Representing Mixed-Integer Linear Programs by Graph Neural Networks.
  Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, and Wotao Yin.
  International Conference on Learning Representations (ICLR), 2023.
• Inventory Balancing with Online Learning.
  Wang Chi Cheung, Will Ma, David Simchi-Levi, and Xinshang Wang.
  Management Science, 68(3):1776–1807, 2022.
• Shrinking the Upper Confidence Bound: A Dynamic Product Selection Problem for Urban Warehouses.
  Rong Jin, David Simchi-Levi, Li Wang, Xinshang Wang, and Sen Yang.
  Management Science, 67(8):4756–4771, 2021.
• Approximation Algorithms for Product Framing and Pricing.
  Guillermo Gallego, Anran Li, Van-Anh Truong, and Xinshang Wang.
  Operations Research, 68(1):134–160, 2020.
• Advance Service Reservations with Heterogeneous Customers.
  Clifford Stein, Van-Anh Truong, and Xinshang Wang.
  Management Science, 66(7):2929–2950, 2020.
• Integrated Scheduling and Capacity Planning with Considerations for Patients’ Length‐of‐Stays.
  Nan Liu, Van-Anh Truong, Xinshang Wang, and Brett R. Anderson.
  Production and Operations Management, 28(7):1735–1756, 2019.
  Wickham-Skinner best paper award
• Multi-Priority Online Scheduling with Cancellations.
  Xinshang Wang and Van-Anh Truong.
  Operations Research, 66(1):104–122, 2018.
• The Lingering of Gradients: How to Reuse Gradients Over Time.
  Zeyuan Allen-Zhu, David Simchi-Levi, and Xinshang Wang.
  Advances in Neural Information Processing Systems (NeurIPS), 31, 2018.
• Provably Near-Optimal Balancing Policies for Multi-Echelon Stochastic Inventory Control Models.
  Retsef Levi, Robin Roundy, Van-Anh Truong, and Xinshang Wang.
  Mathematics of Operations Research, 42(1):256–276, 2017.

Awards

• Gold Medal at National Olympiad in Informatics (NOI). 07/2006
• 1st place at ACM International Collegiate Programming Contest Asia Regional. 10/2010
• 2nd place at ACM International Collegiate Programming Contest Greater New York Region. 10/2011