Follow
Zhong Li
Zhong Li
Microsoft Research Asia
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
On the curse of memory in recurrent neural networks: Approximation and optimization analysis
Z Li, J Han, W E, Q Li
International Conference on Learning Representations (ICLR), 1-43, 2021
412021
Approximation and optimization theory for linear continuous-time recurrent neural networks
Z Li, J Han, W E, Q Li
Journal of Machine Learning Research (JMLR) 23 (42), 1-85, 2022
392022
Complexity measures for neural networks with general activation functions using path-based norms
Z Li, C Ma, L Wu
arXiv preprint arXiv:2009.06132, 1-47, 2020
242020
On the generalization properties of diffusion models
P Li, Z Li, H Zhang, J Bian
Advances in Neural Information Processing Systems (NeurIPS) 36, 1-31, 2023
232023
Approximation theory of convolutional architectures for time series modelling
H Jiang, Z Li, Q Li
International Conference on Machine Learning (ICML) 139, 4961-4970, 2021
132021
A brief survey on the approximation theory for sequence modelling
H Jiang, Q Li, Z Li, S Wang
Journal of Machine Learning (JML) 2 (1), 1-30, 2023
82023
On the approximation properties of recurrent encoder-decoder architectures
Z Li, H Jiang, Q Li
International Conference on Learning Representations (ICLR) (Spotlight), 1-31, 2022
72022
Inverse approximation theory for nonlinear recurrent neural networks
S Wang, Z Li, Q Li
International Conference on Learning Representations (ICLR) (Spotlight), 1-33, 2024
62024
MAC: A unified framework boosting low resource automatic speech recognition
Z Min, Q Ge, Z Li, W E
arXiv preprint arXiv:2302.03498, 1-14, 2023
22023
The system can't perform the operation now. Try again later.
Articles 1–9