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, 2022, 2022
59 2022 Provable Adaptivity of Adam under Non-uniform Smoothness B Wang, Y Zhang, H Zhang, Q Meng, ZM Ma, TY Liu, W Chen
KDD 2024, 2024
28 * 2024 Remax: A simple, effective, and efficient reinforcement learning method for aligning large language models Z Li, T Xu, Y Zhang, Z Lin, Y Yu, R Sun, ZQ Luo
Forty-first International Conference on Machine Learning, 2023
19 * 2023 HyperDQN: A randomized exploration method for deep reinforcement learning Z Li, Y Li, Y Zhang, T Zhang, ZQ Luo
International Conference on Learning Representations, 2021
16 2021 When Expressivity Meets Trainability: Fewer than J Zhang, Y Zhang, M Hong, R Sun, ZQ Luo
Advances in Neural Information Processing Systems, 2021, 2021
9 2021 Why transformers need adam: A hessian perspective Y Zhang, C Chen, T Ding, Z Li, R Sun, ZQ Luo
arXiv preprint arXiv:2402.16788, 2024
7 2024 Fast QLB algorithm and hypothesis tests in logistic model for ophthalmologic bilateral correlated data YQ Lin, YS Zhang, GL Tian, CX Ma
Journal of Biopharmaceutical Statistics 31 (1), 91-107, 2021
4 2021 Does Adam Converge and When? Y Zhang, C Chen, ZQ Luo
ICLR 2022 Blog Track, 2022
2 2022 Adam-mini: Use Fewer Learning Rates To Gain More Y Zhang, C Chen, Z Li, T Ding, C Wu, Y Ye, ZQ Luo, R Sun
arXiv preprint arXiv:2406.16793, 2024
2024 
Zhi-Quan LuoProfessor, The Chinese University of Hong Kong, Shenzhen, ChinaDirección de correo verificada de cuhk.edu.cn
