| Guaranteed matrix completion via non-convex factorization R Sun, ZQ Luo IEEE Transactions on Information Theory 62 (11), 6535-6579, 2016 | 533 | 2016 |
| Optimization for deep learning: An overview RY Sun Journal of the Operations Research Society of China 8 (2), 249-294, 2020 | 390* | 2020 |
| On the convergence of a class of adam-type algorithms for non-convex optimization X Chen, S Liu, R Sun, M Hong arXiv preprint arXiv:1808.02941, 2018 | 373 | 2018 |
| Joint base station clustering and beamformer design for partial coordinated transmission in heterogeneous networks M Hong, R Sun, H Baligh, ZQ Luo IEEE Journal on Selected Areas in Communications 31 (2), 226-240, 2013 | 343 | 2013 |
| Max-sliced wasserstein distance and its use for gans I Deshpande, YT Hu, R Sun, A Pyrros, N Siddiqui, S Koyejo, Z Zhao, ... Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 221 | 2019 |
| Joint downlink base station association and power control for max-min fairness: Computation and complexity R Sun, M Hong, ZQ Luo IEEE Journal on Selected Areas in Communications 33 (6), 1040-1054, 2015 | 117* | 2015 |
| A single-loop smoothed gradient descent-ascent algorithm for nonconvex-concave min-max problems J Zhang, P Xiao, R Sun, Z Luo Advances in neural information processing systems 33, 7377-7389, 2020 | 111 | 2020 |
| Adding one neuron can eliminate all bad local minima S Liang, R Sun, JD Lee, R Srikant Advances in Neural Information Processing Systems 31, 2018 | 101 | 2018 |
| The global landscape of neural networks: An overview R Sun, D Li, S Liang, T Ding, R Srikant IEEE Signal Processing Magazine 37 (5), 95-108, 2020 | 99 | 2020 |
| Robust SINR-constrained MISO downlink beamforming: When is semidefinite programming relaxation tight? E Song, Q Shi, M Sanjabi, RY Sun, ZQ Luo EURASIP Journal on Wireless Communications and Networking 2012, 1-11, 2012 | 97 | 2012 |
| Understanding the loss surface of neural networks for binary classification S Liang, R Sun, Y Li, R Srikant ICML, 2018 | 90 | 2018 |
| On the efficiency of random permutation for ADMM and coordinate descent R Sun, ZQ Luo, Y Ye Mathematics of Operations Research 45 (1), 233-271, 2020 | 79* | 2020 |
| Rmsprop converges with proper hyperparameter N Shi, D Li, R Sun International conference on learning representation, 2021 | 76 | 2021 |
| Adam can converge without any modification on update rules Y Zhang, C Chen, N Shi, R Sun, ZQ Luo Advances in neural information processing systems 35, 28386-28399, 2022 | 71 | 2022 |
| Worst-case complexity of cyclic coordinate descent: gap with randomized version R Sun, Y Ye Mathematical Programming, 1-34, 2019 | 66 | 2019 |
| Global convergence of maml and theory-inspired neural architecture search for few-shot learning H Wang, Y Wang, R Sun, B Li Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022 | 64* | 2022 |
| Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems R Sun, M Hong NIPS, 2015 | 59 | 2015 |
| On the benefit of width for neural networks: Disappearance of bad basins D Li, T Ding, R Sun arXiv preprint arXiv:1812.11039, 2018 | 58* | 2018 |
| Cross-Layer Provision of Future Cellular Networks: A WMMSE-based approach RS Hadi Baligh, Mingyi Hong,Wei-Cheng Liao, Zhi-Quan Luo, Meisam Razaviyayn ... IEEE Signal Processing Magzine 31 (6), 2014 | 56* | 2014 |
| Suboptimal local minima exist for wide neural networks with smooth activations T Ding, D Li, R Sun Mathematics of Operations Research 47 (4), 2784-2814, 2022 | 48* | 2022 |
Zhi-Quan LuoProfessor, The Chinese University of Hong Kong, Shenzhen, ChinaVerified email at cuhk.edu.cn
