| Spider: Near-optimal non-convex optimization via stochastic path-integrated differential estimator C Fang, CJ Li, Z Lin, T Zhang Advances in Neural Information Processing Systems 31, 2018 | 614 | 2018 |
| On the diffusion approximation of nonconvex stochastic gradient descent W Hu, CJ Li, L Li, JG Liu Annals of Mathematical Sciences and Applications 4 (1), 3-32, 2019 | 171* | 2019 |
| On linear stochastic approximation: Fine-grained Polyak-Ruppert and non-asymptotic concentration W Mou, CJ Li, MJ Wainwright, PL Bartlett, MI Jordan Conference on Learning Theory, 2947-2997, 2020 | 84 | 2020 |
| Near-optimal stochastic approximation for online principal component estimation CJ Li, M Wang, H Liu, T Zhang Mathematical Programming 167, 75-97, 2018 | 68 | 2018 |
| Hessian-aware zeroth-order optimization for black-box adversarial attack H Ye, Z Huang, C Fang, CJ Li, T Zhang arXiv preprint arXiv:1812.11377, 2018 | 42 | 2018 |
| A general framework for sample-efficient function approximation in reinforcement learning Z Chen, CJ Li, A Yuan, Q Gu, M Jordan The Eleventh International Conference on Learning Representations, 2023 | 37 | 2023 |
| Statistical sparse online regression: A diffusion approximation perspective J Fan, W Gong, CJ Li, Q Sun International Conference on Artificial Intelligence and Statistics, 1017-1026, 2018 | 31 | 2018 |
| Efficient smooth non-convex stochastic compositional optimization via stochastic recursive gradient descent W Hu, CJ Li, X Lian, J Liu, H Yuan Advances in Neural Information Processing Systems 32, 2019 | 29 | 2019 |
| On the convergence of stochastic extragradient for bilinear games using restarted iteration averaging CJ Li, Y Yu, N Loizou, G Gidel, Y Ma, N Le Roux, M Jordan International Conference on Artificial Intelligence and Statistics, 9793-9826, 2022 | 22* | 2022 |
| ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm C Junchi Li arXiv e-prints, arXiv: 2008.12690v3, 2024 | 20* | 2024 |
| On the fast convergence of random perturbations of the gradient flow J Yang, W Hu, CJ Li Asymptotic Analysis 122 (3-4), 371-393, 2021 | 19* | 2021 |
| Online ICA: Understanding global dynamics of nonconvex optimization via diffusion processes CJ Li, Z Wang, H Liu Advances in Neural Information Processing Systems 29, 2016 | 19 | 2016 |
| Online partial least square optimization: Dropping convexity for better efficiency and scalability Z Chen, LF Yang, CJ Li, T Zhao International Conference on Machine Learning, 777-786, 2017 | 15* | 2017 |
| Diffusion Approximations for Online Principal Component Estimation and Global Convergence CJ Li, M Wang, T Zhang Advances in Neural Information Processing Systems, 645-655, 2017 | 14 | 2017 |
| Optimal Extragradient-Based Stochastic Bilinearly-Coupled Saddle-Point Optimization SS Du, G Gidel, MI Jordan, CJ Li arXiv preprint arXiv:2206.08573, 2022 | 13 | 2022 |
| Nesterov meets optimism: Rate-optimal separable minimax optimization CJ Li, A Yuan, G Gidel, Q Gu, M Jordan International Conference on Machine Learning, 20351-20383, 0 | 10* | |
| Accelerating inexact hypergradient descent for bilevel optimization H Yang, L Luo, CJ Li, M Jordan, M Fazel OPT 2023: Optimization for Machine Learning, 2023 | 9 | 2023 |
| Stochastic modified equations for continuous limit of stochastic ADMM X Zhou, H Yuan, CJ Li, Q Sun arXiv preprint arXiv:2003.03532, 2020 | 8 | 2020 |
| Differential inclusions for modeling nonsmooth ADMM variants: A continuous limit theory H Yuan, Y Zhou, CJ Li, Q Sun International Conference on Machine Learning, 7232-7241, 2019 | 8 | 2019 |
| A convergence analysis of the perturbed compositional gradient flow: Averaging principle and normal deviations W Hu, CJ Li Discrete & Continuous Dynamical Systems - A 38 (10), 4951-4977, 2018 | 7 | 2018 |
