Bypassing the monster: A faster and simpler optimal algorithm for contextual bandits under realizability D Simchi-Levi, Y Xu Mathematics of Operations Research, 2022 | 99 | 2022 |
Instance-dependent complexity of contextual bandits and reinforcement learning: A disagreement-based perspective DJ Foster, A Rakhlin, D Simchi-Levi, Y Xu arXiv preprint arXiv:2010.03104, 2020 | 74 | 2020 |
Offline reinforcement learning: Fundamental barriers for value function approximation DJ Foster, A Krishnamurthy, D Simchi-Levi, Y Xu arXiv preprint arXiv:2111.10919, 2021 | 59 | 2021 |
Online pricing with offline data: Phase transition and inverse square law J Bu, D Simchi-Levi, Y Xu International Conference on Machine Learning, 1202-1210, 2020 | 38 | 2020 |
Phase transitions in bandits with switching constraints D Simchi-Levi, Y Xu Available at SSRN 3380783, 2019 | 36* | 2019 |
Assortment Optimization for a Multistage Choice Model Y Xu, Z Wang Manufacturing & Service Operations Management, 2023 | 13 | 2023 |
Blind network revenue management and bandits with knapsacks under limited switches D Simchi-Levi, Y Xu, J Zhao arXiv preprint arXiv:1911.01067, 2019 | 7* | 2019 |
Data-Driven Dynamic Decision Making: Algorithms, Structures, and Complexity Analysis Y Xu Massachusetts Institute of Technology, 2023 | 1 | 2023 |