| Online optimization with predictions and switching costs: Fast algorithms and the fundamental limit Y Li, G Qu, N Li IEEE Transactions on Automatic Control, 2020 | 123* | 2020 |
| Distributed reinforcement learning for decentralized linear quadratic control: A derivative-free policy optimization approach Y Li, Y Tang, R Zhang, N Li IEEE Transactions on Automatic Control 67 (12), 6429-6444, 2021 | 101 | 2021 |
| Online optimal control with linear dynamics and predictions: Algorithms and regret analysis Y Li, X Chen, N Li Advances in Neural Information Processing Systems 32, 2019 | 99 | 2019 |
| A reliability-aware multi-armed bandit approach to learn and select users in demand response Y Li, Q Hu, N Li Automatica 119, 109015, 2020 | 47* | 2020 |
| On the regret analysis of online LQR control with predictions R Zhang, Y Li, N Li 2021 American Control Conference (ACC), 697-703, 2021 | 46 | 2021 |
| Online optimal control with affine constraints Y Li, S Das, N Li Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 8527-8537, 2021 | 36 | 2021 |
| Online hyperparameter optimization for class-incremental learning Y Liu, Y Li, B Schiele, Q Sun Proceedings of the AAAI Conference on Artificial Intelligence 37 (7), 8906-8913, 2023 | 32 | 2023 |
| Online learning and distributed control for residential demand response X Chen, Y Li, J Shimada, N Li IEEE Transactions on Smart Grid 12 (6), 4843-4853, 2021 | 31 | 2021 |
| Non-asymptotic system identification for linear systems with nonlinear policies Y Li, T Zhang, S Das, J Shamma, N Li IFAC-PapersOnLine 56 (2), 1672-1679, 2023 | 28* | 2023 |
| Growing optimal scale-free networks via likelihood M Small, Y Li, T Stemler, K Judd Physical Review E 91 (4), 042801, 2015 | 25 | 2015 |
| Leveraging predictions in smoothed online convex optimization via gradient-based algorithms Y Li, N Li Advances in Neural Information Processing Systems 33, 14520-14531, 2020 | 22 | 2020 |
| Online learning for markov decision processes in nonstationary environments: A dynamic regret analysis Y Li, N Li 2019 American Control Conference (ACC), 1232-1237, 2019 | 20 | 2019 |
| Online markov decision processes with time-varying transition probabilities and rewards Y Li, A Zhong, G Qu, N Li ICML workshop on Real-world Sequential Decision Making 3, 2019 | 20 | 2019 |
| Mechanism design for reliability in demand response with uncertainty Y Li, N Li 2017 American control conference (ACC), 3400-3405, 2017 | 17 | 2017 |
| Online adaptive policy selection in time-varying systems: No-regret via contractive perturbations Y Lin, JA Preiss, E Anand, Y Li, Y Yue, A Wierman Advances in Neural Information Processing Systems 36, 2024 | 12* | 2024 |
| Online switching control with stability and regret guarantees Y Li, JA Preiss, N Li, Y Lin, A Wierman, JS Shamma Learning for Dynamics and Control Conference, 1138-1151, 2023 | 12 | 2023 |
| Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos Y Liu, Y Li, B Schiele, Q Sun Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | 4 | 2024 |
| Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis Y Li, J Yu, L Conger, T Kargin, A Wierman Proceedings of the 41st International Conference on Machine Learning, PMLR …, 2024 | 4 | 2024 |
| Real-time decision making in control and optimization with performance and safety guarantees Y Li Harvard University, 2021 | 1 | 2021 |
| Online Nonstochastic Control vs. Retrospective Cost Adaptive Control U Syed, Y Li, B Hu IEEE Control Systems Letters, 2024 | | 2024 |
Na LiWinokur Family Professor of Electrical Engineering and Applied Mathematics, HarvardVerified email at seas.harvard.edu
