| Understanding AdamW through Proximal Methods and Scale-Freeness Z Zhuang, M Liu, A Cutkosky, F Orabona Transactions on Machine Learning Research, 2022 | 83 | 2022 |
| Robustness to Unbounded Smoothness of Generalized SignSGD M Crawshaw, M Liu, F Orabona, W Zhang, Z Zhuang Advances in Neural Information Processing Systems 35, 9955--9968, 2022 | 75 | 2022 |
| A second look at exponential and cosine step sizes: Simplicity, adaptivity, and performance X Li, Z Zhuang, F Orabona International Conference on Machine Learning, 6553-6564, 2021 | 40* | 2021 |
| A communication-efficient distributed gradient clipping algorithm for training deep neural networks M Liu, Z Zhuang, Y Lei, C Liao Advances in Neural Information Processing Systems 35, 26204-26217, 2022 | 30 | 2022 |
| No-regret non-convex online meta-learning Z Zhuang, Y Wang, K Yu, S Lu ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 21 | 2020 |
| Surrogate losses for online learning of stepsizes in stochastic non-convex optimization Z Zhuang, A Cutkosky, F Orabona Proceedings of the 36th International Conference on Machine Learning 97 …, 2019 | 6 | 2019 |
| Understanding adamw through proximal methods and scale-freeness. arXiv 2022 Z Zhuang, M Liu, A Cutkosky, F Orabona arXiv preprint arXiv:2202.00089, 0 | 6 | |
| Online meta-learning on non-convex setting Z Zhuang, K Yu, S Lu, L Glass, Y Wang Workshop on Meta-Learning at NeurIPS 2019, 2019 | 5 | 2019 |
| Adaptive Strategies in Non-convex Optimization Z Zhuang Boston University, 2023 | 4 | 2023 |
Francesco OrabonaAssociate Professor, KAUSTVerified email at orabona.com