Skip to content

Publications

(Asterisk * indicates alphabetical authorship)

Journal papers and preprints

  • Qiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang, “Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium”, manuscript, 2020. [arxiv]
    • Preliminary version: Proceedings of the Conference on Learning Theory (COLT) 2020.
  • Devavrat Shah*, Qiaomin Xie*, Zhi Xu*, “Non-Asymptotic Analysis of Monte Carlo Tree Search”, manuscript, 2020. [arxiv]
  • Devavrat Shah*, Qiaomin Xie*, Zhi Xu*, “Stable Reinforcement Learning with Unbounded State Space”, manuscript, 2020. [arxiv]
    • Preliminary version: Conference on Learning for Dynamics and Control (L4DC) 2020.
  • Bai Liu, Qiaomin Xie, Eytan Modiano, “Reinforcement Learning for Optimal Control of Queueing Systems”, manuscript, 2020. [arxiv]
    • Preliminary version: Proceedings of Allerton Conference 2019.
  • Devavrat Shah*, Qiaomin Xie*, “Centralized Congestion Control and Scheduling in a Datacenter”, manuscript, 2020.
  • Varun Gupta*, Benjamin Moseley*, Marc Uetz*, Qiaomin Xie*, “Stochastic Online Scheduling on Unrelated Machines”, Mathematics of Operations Research, 2020.
  • Qiaomin Xie, Mayank Pundir, Yi Lu, Cristina L. Abad, Roy H. Campbell, “Pandas: Robust Locality-Aware Scheduling with Stochastic Delay Optimality”, IEEE/ACM Transactions on Networking, April 2017.

Conference papers

  • Qiaomin Xie, Zhuoran Yang, Zhaoran Wang, Andreea Minca, “Learning While Playing in Mean-Field Games: Convergence and Optimality”,  ICML, July 2021. [arxiv]
  • Weina Wang, Qiaomin Xie, Mor Harchol-Balter, “Zero Queueing for Multi-server Jobs”, ACM SIGMETRICS, June 2021. [arxiv]
  • Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang, Qiaomin Xie, “Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret”, NeurIPS, December 2020 (spotlight). [arxiv]
  • Yingjie Fei, Zhuoran Yang, Zhaoran Wang, Qiaomin Xie, “Dynamic Regret of Policy Optimization in Non-stationary Environments”, NeurIPS, December 2020. [arxiv]

  • Weichao Mao, Kaiqing Zhang, Qiaomin Xie, Tamer Başar, “POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis”, NeurIPS, December 2020. [arxiv]

  • Devavrat Shah*, Varun. Somani*, Qiaomin Xie*, Zhi Xu*, “On Reinforcement Learning for Turn-based Zero-Sum Markov Games”, to appear in Proceedings of ACM-IMS Foundations of Data Science Conference, October 2020. [arxiv]

  • Qiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang, “Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium”, Proceedings of the Conference on Learning Theory (COLT), July 2020.
    • Accepted as full paper; Appeared as extended abstract
  • Devavrat Shah*, Qiaomin Xie*, Zhi Xu*, “Non-Asymptotic Analysis of Monte Carlo Tree Search”, Proceedings of ACM SIGMETRICS, June 2020.
    • Accepted as full paper; Appeared as extended abstract
  • Bai Liu, Qiaomin Xie, Eytan Modiano, “Reinforcement Learning for Optimal Control of Queueing Systems”, Proceedings of Allerton Conference,  September 2019.
  • Devavrat Shah*, Qiaomin Xie*, “Q-Learning with Nearest Neighbors”, Proceedings of Conference on Neural Information Processing Systems (NeurIPS), December 2018. [arxiv].
  • Varun Gupta*, Benjamin Moseley*, Marc Uetz*, Qiaomin Xie*, “Competitive greedy algorithms for stochastic unrelated machine scheduling”, the 13th Workshop on Models and Algorithms for Planning and Scheduling Problems (MAPSP), June 2017.
  • Varun Gupta*, Benjamin Moseley*, Marc Uetz*, Qiaomin Xie*, “Stochastic Online Scheduling on Unrelated Machines”, Conference on Integer Programming and Combinatorial Optimization (IPCO), June 2017.
  • Qiaomin Xie, Ali Yekkehkhany, Yi Lu, “Scheduling with Multi-level Data Locality: Throughput optimality and Heavy-traffic Optimality”, Proceedings of IEEE INFOCOM, April 2016.
  • Qiaomin Xie, Xiaobo Dong, Yi Lu, R. Srikant, “Power of d Choices for Large-Scale Bin Packing: A Loss Model”, ACM SIGMETRICS (full paper), June 2015.
  • Qiaomin Xie, Yi Lu, “Priority Algorithm for Near-data Scheduling: Throughput optimality and Heavy-traffic Optimality”, Proceedings of IEEE INFOCOM, April 2015.
  • Qiaomin Xie, Yi Lu, “Degree-guided Map-Reduce Task Assignment with Data Locality Constraint”, Proceedings of IEEE ISIT, July 2012.
  • Yi Lu, Qiaomin Xie, Gabriel Kliot, Alan Geller, James Larus, Albert Greenberg, “Join-Idle-Queue: A Novel Load Balancing Algorithm for Dynamically Scalable Web Services”, Performance Evaluation, 2011. 29th International Symposium on Computer Performance, Modeling, Measurements, and Evaluation, October 2011. Best Paper Award