Research

Working papers

Listed in reverse chronological order

• Achieving Õ(1/ε) Sample Complexity for Constrained Markov Decision Process,
  Jiashuo Jiang, Yinyu Ye [Paper]
  

• Constrained Online Two-stage Stochastic Optimization: Algorithms with (and without) Predictions,
  Piao Hu, Jiashuo Jiang, Guodong Lyu, Hao Su [Paper]
  

• Constant Approximation for Network Revenue Management with Markovian-correlated Customer Arrivals,
  Jiashuo Jiang [Paper]
  

• Degeneracy is OK: Logarithmic Regret for Network Revenue Management with Indiscrete Distributions,
  Jiashuo Jiang, Will Ma, Jiawei Zhang [Paper]
  

• Tightness without Counterexamples: A New Approach and New Results for Prophet Inequalities,
  Jiashuo Jiang, Will Ma, Jiawei Zhang [Paper]
  

• Online Resource Allocation with Stochastic Resource Consumption,
  Jiashuo Jiang, Jiawei Zhang [Paper]
  

Journal Publications

• Online Stochastic Optimization with Wasserstein Based Non-stationarity,
  Jiashuo Jiang, Xiaocheng Li, Jiawei Zhang [Paper]
  Management Science, 2024 (accepted).

• Tight Guarantees for Multi-unit Prophet Inequalities and Online Stochastic Knapsack,
  Jiashuo Jiang, Will Ma, Jiawei Zhang [Paper]
  Operations Research, 2024.

  Finalist for the George Nicholson Student Paper Competition
  Finalist for the Jeff McGill Student Paper Competition

• Learning to Order for Inventory Systems with Lost Sales and Uncertain Supplies
  Boxiao Chen, Jiashuo Jiang, Jiawei Zhang, Zhengyuan Zhou [Paper]
  Management Science, 2023.

• Achieving High Individual Service-Levels without Safety Stock? Optimal Rationing Policy of Pooled Resources
  Jiashuo Jiang, Shixin Wang, Jiawei Zhang [Paper]
  Operations Research, 2022.

Conference Publications

• Scheduling in LLM Inference with Blowed-up Memory Constraints,
  Zijie Zhou, Jiashuo Jiang
  NeurIPS 2024 Workshop on Statistical Frontiers of LLM and Foundation Models.

• Achieving Õ(1/ε) Sample Complexity for Constrained Markov Decision Process,
  Jiashuo Jiang, Yinyu Ye [Paper]
  Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS 2024).

• High-dimensional Linear Bandits with Knapsacks,
  Wanteng Ma, Dong Xia, Jiashuo Jiang [Paper]
  2024 International Conference on Machine Learning (ICML 2024).

• Tightness without Counterexamples: A New Approach and New Results for Prophet Inequalities,
  Jiashuo Jiang, Will Ma, Jiawei Zhang [Paper]
  The Twenty-Fourth ACM Conference on Economics and Computation (EC 2023).

• Non-stationary Bandits with Knapsacks,
  Shang Liu, Jiashuo Jiang, Xiaocheng Li [Paper]
  Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022).

• Tight Guarantees for Multi-unit Prophet Inequalities and Online Stochastic Knapsack,
  Jiashuo Jiang, Will Ma, Jiawei Zhang [Paper]
  ACM-SIAM Symposium on Discrete Algorithms (SODA 2022) [Link].