Research

Papers

Working Papers

  1. Y. Duan, Y. Hu, J. Jiang. Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control.
    • Submitted.
  2. C. Hssaine, Y. Hu, C. Pike-Burke. Learning Fair And Effective Points-Based Rewards Programs.
    • Major Revision at Operations Research.
    • Preliminary version: EC, 2025.
  3. Y. Hu, N. Kallus, X. Mao, Y. Wu. Contextual Linear Optimization under Partial Feedback.
    • Major Revision at Management Science.
    • Preliminary version: Contextual Linear Optimization with Bandit Feedback, NeurIPS, 2024.
  4. Y. Hu, N. Kallus. DTR Bandit: Learning to Make Response-Adaptive Decisions with Low Regret.
    • Under Revision.

Publications

  1. Y. Hu, N. Kallus, M. Uehara (2025). Fast Rates for the Regret of Offline Reinforcement Learning.
    • Mathematics of Operations Research 50(1):633-655.
    • Preliminary version: COLT, 2021.
    • Recorded talks: RL Theory Seminar [60-min video], COLT [18-min video]
  2. Y. Hu, N. Kallus, X. Mao (2022). Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes.
    • Operations Research 70(6):3261-3281.
    • Finalist, INFORMS Applied Probability Society Best Student Paper Competition, 2020.
    • Preliminary version: COLT, 2020.
    • Recorded talk: COLT [15-min video]
  3. Y. Hu, N. Kallus, X. Mao (2022). Fast Rates for Contextual Linear Optimization.
    • Management Science 68(6):4236-4245.
  4. M. Garrard, H. Wang, B. Letham, Z. Wang, Y. Huang, Y. Hu, C. Zhou, N. Zhou, E. Bakshy (2021). Practical Policy Optimization with Personalized Experimentation.
    • NeurIPS Workshop on Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice.