Publications
Check my Google Scholar profile for more information! (* stands for equal contribution.)
Mechanism Design, Pricing, and Resource Allocation
-
Efficiency, Feasibility, Incentive-Awareness in Constrained Online Resource Allocation
, Negin Golrezaei, Patrick Jaillet.
Under Review at Operations Research.
Early version accepted to NeurIPS 2025 (under the title “Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints”).
1st place in ACM Student Research Competition (SRC), SIGMETRICS 2025.Other presentations
- Asia-Pacific Operations Research Societies (APORS) Youth Forum, Singapore (Nov 2026)
- Cornell ORIE Young Researchers Workshop, Ithaca, NY (Oct 2026)
- As a finalist, Citadel Securities PhD Summit, Miami, FL (Apr 2026)
- As a finalist, TwoSigma PhD Fellowship Final Presentation, New York, NY (Feb 2026)
- As an invited speaker, UMass Amherst Theory Seminar, Amherst, MA (Oct 2025)
- As an invited talk, INFORMS Annual Meeting, Atlanta, GA (Oct 2025)
-
Non-Monetary Mechanism Design without Priors: Achieving Efficiency via Adaptive Costly Audits
, Moïse Blanchard, Patrick Jaillet.
Major Revision at Operations Research.
Early version accepted to COLT 2025 (under the title “Non-Monetary Mechanism Design without Distributional Information: Using Scarce Audits Wisely”). -
The Power of Two Choices in Dynamic Pricing: As Good As Full Feedback, Instance-Wise
, Tao Lin, Aleksandrs Slivkins. -
The Speed of Social Learning with Pricing
, Nicole Immorlica, Brendan Lucier, Aleksandrs Slivkins. -
Market Design for AI: Beyond the Copyright Binary
, Maryam Farboodi, Negin Golrezaei, Sepehr Shahshahani.
Early version accepted to 2026 M&SOM Service Operations SIG (acceptance rate: 10/96).Other presentations
- As an invited talk, INFORMS Annual Meeting, San Francisco, CA (Nov 2026)
- Eleventh Marketplace Innovation Workshop, online (May 2026)
Bandits and Online Learning Theory
-
Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks
and Longbo Huang.
In Proceedings of the ACM on Measurement and Analysis of Computing Systems, 8(3):31 2024.
Best Paper Award of ACM SIGMETRICS 2025. -
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
Yu Chen*, Jiatai Huang*, , Longbo Huang. -
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
Jiatai Huang*, , Longbo Huang. -
Variance-Aware Sparse Linear Bandits
, Ruosong Wang, Simon S. Du. -
Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
Jiatai Huang*, , Longbo Huang. -
Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
, Negin Golrezaei, Patrick Jaillet.
Reinforcement Learning Theory
-
Introducing Feedback Delays to Non-Delayed Adversarial MDPs: Optimal √S and √K Dependencies in Tabular and Linear AMDPs
Aarush Kulkarni, Khang Nguyen, William Chang, . -
Refined Sample Complexity for Markov Games with Independent Linear Function Approximation
, Qiwen Cui, Simon S. Du. -
Refined Regret for Adversarial MDPs with Linear Function Approximation
, Haipeng Luo, Chen-Yu Wei, Julian Zimmert. -
Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
, Haipeng Luo, Liyu Chen.
Optimization for Deep Learning
-
Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, . -
The Crucial Role of Normalization in Sharpness-Aware Minimization
, Kwangjun Ahn*, Suvrit Sra.