Papers

(￥\alpha￥-￥\beta￥: author names are sorted alphabetically)

Working Papers

• Achieving Low Regret for Contextual Network Revenue Management
  Adam Elmachtoub, Rachitesh Kumar, Haixiang Lan (￥\alpha￥-￥\beta￥)
  Submitted
  

• Data-Driven Admission Control under Cost Uncertainty
  Adam Elmachtoub, Rachitesh Kumar, Haixiang Lan (￥\alpha￥-￥\beta￥)
  To be Submitted
  

• Data-Driven Robust Group Selection
  Adam Elmachtoub, Rachitesh Kumar, Haixiang Lan (￥\alpha￥-￥\beta￥)
  In Preparation
  

• Pretrain-Then-Calibrate: Enhancing Optimality-Feasibility Tradeoff in Safe Contextual Optimization
  Haixiang Lan, Tianyu Wang, Henry Lam
  Submitted
  Preliminary version appeared in NeurIPS 2026 OPT Workshop on Optimization for Machine Learning
  

Publications

• The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  Haixiang Lan, Luofeng Liao, Adam Elmachtoub, Christian Kroer, Henry Lam, Haofeng Zhang
  Accepted to The 39th Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
  

• Dissecting the Impact of Model Misspecification in Data-Driven Optimization
  Adam Elmachtoub, Henry Lam, Haixiang Lan, Haofeng Zhang (￥\alpha￥-￥\beta￥)
  Accepted to The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
  

• LP-based Control for Network Revenue Management under Markovian Demands
  Haixiang Lan , Guillermo Gallego, Zizhuo Wang, Yinyu Ye
  Accepted to The 20th Conference on Web and Internet Economics (WINE), 2024
  

• A Tuning-Free Primal-Dual Splitting Algorithm for Large-Scale Semidefinite Programming
  Haixiang Lan, Yinjun Wang, Yinyu Ye (￥\alpha￥-￥\beta￥)
  Accepted to INFORMS Optimization Society (IOS), 2024