Publications

Check my Google Scholar profile for more information!

(* stands for equal contribution. Listed reverse chronologically.)

Journal Publications and Working Papers

• Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints (draft available upon request)
  Yan Dai, Negin Golrezaei, and Patrick Jaillet.
  1st place in ACM Student Research Competition (SRC), SIGMETRICS 2025.
  (slides)
• Non-Monetary Mechanism Design without Distributional Information: Using Scarce Audits Wisely
  Yan Dai, Moise Blanchard, and Patrick Jaillet.
  Early version accepted to conference COLT 2025.
  (slides)
• Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks
  Yan Dai and Longbo Huang.
  In Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS), 8(3):31, 2024.
  Best Paper Award of conference ACM SIGMETRICS 2025.
  (extended abstract, slides (20min), video (5min))

Conference Publications

• uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
  Yu Chen*, Jiatai Huang*, Yan Dai*, and Longbo Huang.
  Accepted to conference ICLR 2025 (Spotlight).
• Refined Sample Complexity for Markov Games with Independent Linear Function Approximation
  Yan Dai, Qiwen Cui, and Simon S. Du.
  Accepted to conference COLT 2024.
  (extended abstract, slides)
• Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
  Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, and Yan Dai.
  Accepted to conference ICML 2024.
• The Crucial Role of Normalization in Sharpness-Aware Minimization
  Yan Dai*, Kwangjun Ahn*, and Suvrit Sra.
  Accepted to conference NeurIPS 2023.
  (slides, video)
• Refined Regret for Adversarial MDPs with Linear Function Approximation
  Yan Dai, Haipeng Luo, Chen-Yu Wei, and Julian Zimmert.
  Accepted to conference ICML 2023.
  (slides (60min), slides (5min), video)
• Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
  Jiatai Huang*, Yan Dai*, and Longbo Huang.
  Accepted to conference ICML 2023.
  (slides, video)
• Variance-Aware Sparse Linear Bandits
  Yan Dai, Ruosong Wang, and Simon S. Du.
  Accepted to conference ICLR 2023.
  (slides (60min), slides (5min), video)
• Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
  Yan Dai, Haipeng Luo, and Liyu Chen.
  Accepted to conference NeurIPS 2022.
  (slides, video)
• Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
  Jiatai Huang*, Yan Dai*, and Longbo Huang.
  Accepted to conference ICML 2022.
  (video)