{"id":8,"date":"2021-08-25T01:16:07","date_gmt":"2021-08-25T01:16:07","guid":{"rendered":"https:\/\/mitmgmtfaculty.mit.edu\/tlykouris\/research-publications\/"},"modified":"2026-03-17T15:57:30","modified_gmt":"2026-03-17T15:57:30","slug":"research","status":"publish","type":"page","link":"https:\/\/mitmgmtfaculty.mit.edu\/tlykouris\/research\/","title":{"rendered":"Research"},"content":{"rendered":"

Journal Articles<\/h2>
    \n
  1. \"Efficient Decentralized Multi-agent Learning in Asymmetric Bipartite Queueing Systems<\/a>.\"
    \nwith Daniel Freund and Wentao Weng.
    \nOperations Research<\/strong>. <\/strong><\/em>Vol. 72, No. 3 (2024): 1049-1070.
    \nConference version: 35th Annual Conference on Learning Theory (COLT 2022).<\/em>
    \n    Journal version<\/a>
    \n    Video<\/a> of a 60-minute talk that Daniel gave in the SNAPP seminar series in April 2023<\/a>.
    \nFinalist in the Applied Probability Society Student Paper Competition (2022)<\/strong>.<\/strong><\/li>\n
  2. \"Learning in Stackelberg Games with Non-myopic Agents\"<\/a>
    \nwith Nika Haghtalab,, Sloan Nietert, and Alexander Wei.
    \nOperations Research<\/strong>.\u00a0<\/strong><\/em>Forthcoming (2025).
    \nConference version: 23rd ACM Conference on Economics and Computation (EC 2022).<\/em><\/li>\n
  3. \u201cStatic Pricing for Multi-unit Prophet Inequalities<\/a>.\u201d
    \nwith Shuchi Chawla and Nikhil Devanur.
    \nOperations Research<\/strong>. <\/strong><\/em>Vol. 72, No. 4 (2024): 1388-1399.
    \nConference version: 17th Conference on Web and Internet Economics (WINE 2021).<\/em>
    \n    Journal version<\/a>.<\/li>\n
  4. \"Corruption-robust Exploration in Episodic Reinforcement Learning<\/a>.\"
    \nwith Max Simchowitz, Aleksandrs Slivkins, and Wen Sun.
    \nMathematics of Operations Research. <\/strong>Vol. 50, No. 2 (2024): 1277-1304.
    \nConference version: 34th Annual Conference on Learnint Theory (COLT 2021).<\/em>
    \n    Journal version<\/a>.
    \n    Video<\/a> of a 60-minute talk that I gave in the RL Theory seminar series in November 2020<\/a>.<\/li>\n
  5. \"Contextual Search in the Presence of Adversarial Corruptions<\/a>.\"
    \nwith Akshay Krishnamurthy, Chara Podimata, and Robert Schapire.
    \nOperations Research.<\/strong> Vol. 71, No. 4 (2023): 1120-1135.
    \nConference version: 53rd ACM Symposium on Theory of Computing (STOC 2021).<\/em>
    \n    Journal version.<\/a>
    \n    Video<\/a> of a 45-minute talk that Chara gave at the Simons Institute in September 2022<\/a>.<\/li>\n
  6. \"Competitive Caching with Machine Learned Advice<\/a>.\"
    \nwith Sergei Vassilvitskii.
    \nJournal of the ACM.<\/strong> Vol. 68, No. 4, Art. 24 (2021): 1-25.
    \nConference version: 35th International Conference on Machine Learning (ICML 2018).<\/em>
    \n    Journal version<\/a>.<\/li>\n
  7. \"Small-loss Bounds for Online Learning with Partial Information<\/a>.\"
    \nwith Karthik Sridharan and \u00c9va Tardos.
    \nMathematics of Operations Research<\/strong>. Vol. 47, No. 3 (2022): 2186-2218.
    \nConference version: 31st Annual Conference on Learning Theory (2018).<\/em>
    \n    Journal version<\/a>.
    \n    Video<\/a> of a 10-minute talk that I gave at the COLT 2018 conference in July 2018<\/a>.
    \nFinalist in the INFORMS Nicholson Student Paper Competition (2018).<\/strong><\/strong><\/strong><\/li>\n
  8. \"Pricing and Optimization in Shared Vehicle Systems: An Approximation Framework<\/a>.\"
    \nwith Siddhartha Banerjee and Daniel Freund.
    \nOperations Research.<\/strong> Vol. 70, No. 3 (2022): 1783-1805.
    \nConference version: 18th ACM Conference on Economics and Computation (EC 2017).<\/em>
    \n    Journal version<\/a>.
    \n    Video<\/a> of a 20-minute talk that I gave at the EC 2017 conference in June 2017<\/a>.
    \nFinalist in the Applied Probability Society Student Paper Competition (2017).<\/strong><\/li>\n<\/ol>\n<\/div><\/div>

    Working Papers<\/h2>
      \n
    1. \"Scheduling with Uncertain Holding Costs and its Application to Content Moderation<\/a>.\"
      \nwith Caner Gocmen, Deeksha Sinha, and Wentao Weng.
      \nMajor Revision at Management Science.<\/strong><\/em>
      \n      Video<\/a> of a 45-minute talk that I gave at the Simons Institute in January 2026<\/a>.<\/li>\n
    2. \"Learning to Defer in Congested Systems: The AI-Human Interplay<\/a>.\"
      \nwith Wentao Weng.
      \nUnder second-round review at Operations Research (after Major Revision).<\/strong><\/em>
      \n      Video<\/a> of a 60-minute talk that I gave in the SNAPP seminar series in May 2024<\/a>.
      \nFinalist in the Junior Faculty Interest Group Paper Competition (2024)<\/strong>.<\/strong><\/li>\n
    3. \"Social Learning with Limited Attention: Negative Reviews Persist under Newest First<\/a>.\"
      \nwith Jackie Baek and Atanas Dinev.
      \nUnder second-round review at Operations Research (after Major Revision).<\/strong><\/em><\/b>
      \nConference version: 25th ACM Conference on Economics and Computation (EC 2024).<\/em>
      \nAccepted for presentation in the 2025 MSOM SIG (Service Science)<\/strong>.<\/em>
      \nFinalist in the Junior Faculty Interest Group Paper Competition (2025)<\/strong>.<\/strong><\/li>\n
    4. \"The Transient Cost of Learning in Queueing Systems<\/a>.\"
      \nwith Daniel Freund and Wentao Weng.
      \nUnder second-round review at Operations Research (after Reject-and-Resubmit).<\/strong><\/em><\/b>
      \nConference version: 37th Conference on Neural Information Processing Systems (NeurIPS 2023).<\/em><\/li>\n
    5. \"Group Fairness in Dynamic Refugee Assignment<\/a>.\"
      \nwith Daniel Freund, Elisabeth Paulson, Bradley Sturt, and Wentao Weng.
      \nMajor Revision at Operations Research.<\/strong><\/em>
      \nConference version: 24th ACM Conference on Economics and Computation (EC 2023).<\/em>
      \n      Video<\/a> of a 60-minute talk that Daniel gave at the TOC4Fairness in February 2024<\/a>.
      \n      Video<\/a> of a 18-minute talk that Wentao gave at the EC 2023 conference in June 2023<\/a>.<\/li>\n
    6. \u201cStochastic Bandits Robust to Adversarial Corruptions<\/a>.\u201d
      \nwith Vahab Mirrokni and Renato Paes Leme.
      \nConference version: 50th ACM Symposium on Theory of Computing (STOC 2018).<\/em>
      \n      Video<\/a> of a 75-minute bootcamp talk that I gave at the Simons Institute in August 2022<\/a>.
      \n      Video<\/a> of a 20-minute talk that I gave at the STOC 2018 conference in June 2018<\/a>.<\/li>\n
    7. \u201cLearning and Efficiency in Games with Dynamic Population<\/a>.\u201d
      \nwith Vasilis Syrgkanis, and \u00c9va Tardos.
      \nMajor Revision at Mathematics of Operations Research.<\/strong><\/em>
      \nConference version: 27th ACM-SIAM Symposium on Discrete Algorithms (SODA 2016).<\/em>
      \n      Video<\/a> of a 45-minute talk that \u00c9va gave at the Simons Institute in March 2018<\/a>.<\/li>\n<\/ol>\n<\/div><\/div>

      Conference Publications Not Listed Above<\/h2>
        \n
      1. \"Contextual Dynamic Pricing with Heterogeneous Buyers.<\/a>\"
        \nwith Sloan Nietert, Princewill Okoroafor, Chara Podimata, and Julian Zimmert.
        \n39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)<\/strong>.<\/li>\n
      2. \"Bayesian Decision-Making under Misspecified Priors with Applications to Meta-Learning<\/a>.\"
        \nMax Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris<\/em>, Miroslav Dud\u00edk, Robert Schapire (contributional author order)<\/em>.
        \n35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021)<\/strong>.<\/li>\n
      3. \"Constrained Episodic Reinforcement Learning in Concave-convex and Knapsack Settings.<\/a>\"
        \nwith Kiant\u00e9 Brantley, Miroslav Dud\u00edk, Sobhan Miryoosefi, Max Simchowitz, Aleksandrs Slivkins, and Wen Sun.
        \n34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)<\/strong>.<\/li>\n
      4. \"Bandits with Adversarial Scaling<\/a>.\"
        \nwith Vahab Mirrokni and Renato Paes Leme.
        \n37th International Conference on Machine Learning (ICML 2020)<\/strong>.
        \n        Video<\/a> of a 15-minute talk that I gave at the ICML 2020 conference in July 2020<\/a>.<\/li>\n
      5. \"Feedback Graph Regret Bounds for Thompson Sampling and UCB<\/a>.\"
        \nwith \u00c9va Tardos and Drishti Wali.
        \n31st International Conference on Algorithmic Learning Theory (ALT 2020)<\/strong>.<\/li>\n
      6. \"Advancing Subgroup Fairness via Sleeping Experts.<\/a>\"
        \nwith Avrim Blum.
        \n11th Innovations in Theoretical Computer Science Conference (ITCS 2020)<\/strong>.<\/li>\n
      7. \"On Preserving Non-discrimination when Combining Expert Advice.<\/a>\"
        \nwith Avrim Blum, Suriya Gunasekar, and Nathan Srebro.
        \n32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018)<\/strong>.<\/li>\n
      8. \"Learning in Games: Robustness of Fast Convergence.<\/a>\"
        \nwith Dylan Foster, Zhiyuan Li, Karthik Sridharan, and \u00c9va Tardos.
        \n30th Annual Conference on Neural Information Processing Systems (NeurIPS 2016)<\/strong>.
        \n        Video<\/a> of a 30-minute talk that I gave at the YoungEC 2017 workshop in January 2017<\/a>.<\/li>\n
      9. \"Influence Maximization in Switching-selection Threshold Models.<\/a>\"
        \nwith Dimitris Fotakis, Evangelos Markakis, and Svetlana Obraztsova.
        \n7th International Symposium on Algorithmic Game Theory (SAGT 2014)<\/strong>.<\/li>\n<\/ol>\n<\/div><\/div>

        PhD Dissertation<\/h2>