| Toward understanding the importance of noise in training neural networks M Zhou, T Liu, Y Li, D Lin, E Zhou, T Zhao International Conference on Machine Learning (ICML), 7594-7602, 2019 | 88 | 2019 |
| Deep reinforcement learning with robust and smooth policy Y Li*, Q Shen*, H Jiang, Z Wang, T Zhao International Conference on Machine Learning (ICML), 8707-8718, 2020 | 73* | 2020 |
| Implicit bias of gradient descent based adversarial training on separable data Y Li, EX Fang, H Xu, T Zhao International Conference on Learning Representations (ICLR), 2020 | 49* | 2020 |
| Non-convex conditional gradient sliding C Qu, Y Li, H Xu International Conference on Machine Learning (ICML), 4208-4217, 2018 | 30 | 2018 |
| First-order policy optimization for robust Markov decision process Y Li, G Lan, T Zhao arXiv preprint arXiv:2209.10579, 2022 | 28 | 2022 |
| Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity Y Li, G Lan, T Zhao Mathematical Programming, Series A, 2023 | 22* | 2023 |
| Permutation invariant policy optimization for mean-field multi-agent reinforcement learning Y Li, L Wang, J Yang, E Wang, Z Wang, T Zhao, H Zha arXiv preprint arXiv:2105.08268, 2021 | 20 | 2021 |
| Pessimism meets invariance: provably efficient offline mean-field multi-agent RL M Chen, Y Li, E Wang, Z Yang, Z Wang, T Zhao Advances in Neural Information Processing Systems (NeurIPS) 34, 17913-17926, 2021 | 17 | 2021 |
| Noisy gradient descent converges to flat minima for nonconvex matrix factorization T Liu, Y Li, S Wei, E Zhou, T Zhao International Conference on Artificial Intelligence and Statistics (AISTAT …, 2021 | 11 | 2021 |
| Block policy mirror descent G Lan, Y Li, T Zhao SIAM Journal on Optimization, 2023 | 8 | 2023 |
| Implicit regularization of bregman proximal point algorithm and mirror descent on separable data Y Li, C Ju, EX Fang, T Zhao arXiv preprint arXiv:2108.06808, 2021 | 8 | 2021 |
| First-order policy optimization for robust policy evaluation Y Li, G Lan arXiv preprint arXiv:2307.15890, 2023 | 7 | 2023 |
| Policy mirror descent inherently explores action space Y Li, G Lan arXiv preprint arXiv:2303.04386, 2023 | 7 | 2023 |
| Robust multi-agent reinforcement learning via adversarial regularization: theoretical foundation and stable algorithms A Bukharin, Y Li, Y Yu, Q Zhang, Z Chen, S Zuo, C Zhang, S Zhang, ... Advances in Neural Information Processing Systems (NeurIPS), 2023 | 6 | 2023 |
| Frequency-aware SGD for efficient embedding learning with provable benefits Y Li, D Choudhary, X Wei, B Yuan, B Bhushanam, T Zhao, G Lan International Conference on Learning Representations (ICLR), 2022 | 4 | 2022 |
| Rectangularity and duality of distributionally robust Markov decision processes Y Li, A Shapiro arXiv preprint arXiv:2308.11139, 2023 | 2 | 2023 |
| Distributionally robust stochastic optimal control A Shapiro, Y Li arXiv preprint arXiv:2406.05648, 2024 | | 2024 |
| A novel catalyst scheme for stochastic minimax optimization G Lan, Y Li arXiv preprint arXiv:2311.02814, 2023 | | 2023 |
| Noise regularizes over-parameterized rank one matrix recovery, provably T Liu, Y Li, E Zhou, T Zhao International Conference on Artificial Intelligence and Statistics (AISTAT …, 2022 | | 2022 |
