Huishuai Zhang
Huishuai Zhang
Microsoft Research Asia
Adresse e-mail validée de - Page d'accueil
Citée par
Citée par
Reshaped wirtinger flow for solving quadratic system of equations
H Zhang, Y Liang
Advances in Neural Information Processing Systems 29, 2622-2630, 2016
On layer normalization in the transformer architecture
R Xiong, Y Yang, D He, K Zheng, S Zheng, C Xing, H Zhang, Y Lan, ...
International Conference on Machine Learning, 10524-10533, 2020
Provable non-convex phase retrieval with outliers: Median truncatedwirtinger flow
H Zhang, Y Chi, Y Liang
International conference on machine learning, 1022-1031, 2016
A nonconvex approach for phase retrieval: Reshaped wirtinger flow and incremental algorithms
H Zhang, Y Zhou, Y Liang, Y Chi
Journal of Machine Learning Research 18, 2017
SGD converges to global minimum in deep learning via star-convex path
Y Zhou, J Yang, H Zhang, Y Liang, V Tarokh
arXiv preprint arXiv:1901.00451, 2019
The capacity region of the source-type model for secret key and private key generation
H Zhang, L Lai, Y Liang, H Wang
IEEE Transactions on Information Theory 60 (10), 6389-6398, 2014
Reshaped Wirtinger flow and incremental algorithm for solving quadratic system of equations
H Zhang, Y Zhou, Y Liang, Y Chi
arXiv preprint arXiv:1605.07719, 2016
Median-truncated nonconvex approach for phase retrieval with outliers
H Zhang, Y Chi, Y Liang
IEEE Transactions on information Theory 64 (11), 7287-7310, 2018
Geometrical properties and accelerated gradient solvers of non-convex phase retrieval
Y Zhou, H Zhang, Y Liang
2016 54th Annual Allerton Conference on Communication, Control, and …, 2016
Non-convex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent
Y Li, Y Chi, H Zhang, Y Liang
Information and Inference: A Journal of the IMA 9 (2), 289-325, 2020
Block-diagonal hessian-free optimization for recurrent and convolutional neural networks
H Zhang, C Xiong
US Patent App. 15/983,782, 2018
-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Q Meng, S Zheng, H Zhang, W Chen, ZM Ma, TY Liu
arXiv preprint arXiv:1802.03713, 2018
Generalization error bounds with probabilistic guarantee for SGD in nonconvex optimization
Y Zhou, Y Liang, H Zhang
arXiv preprint arXiv:1802.06903, 2018
Training over-parameterized deep resnet is almost as easy as training a two-layer network
H Zhang, D Yu, W Chen, TY Liu
Multi-key generation over a cellular model with a helper
H Zhang, Y Liang, L Lai, SS Shitz
IEEE Transactions on Information Theory 63 (6), 3804-3822, 2017
Analysis of robust pca via local incoherence
H Zhang, Y Zhou, Y Liang
Advances in Neural Information Processing Systems 28, 1819-1827, 2015
Capacity control of relu neural networks by basis-path norm
S Zheng, Q Meng, H Zhang, W Chen, N Yu, TY Liu
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 5925-5932, 2019
Secret key capacity: Talk or keep silent?
H Zhang, Y Liang, L Lai
2015 IEEE International Symposium on Information Theory (ISIT), 291-295, 2015
Block-diagonal hessian-free optimization for training neural networks
H Zhang, C Xiong, J Bradbury, R Socher
arXiv preprint arXiv:1712.07296, 2017
Convergence of distributed stochastic variance reduced methods without sampling extra data
S Cen, H Zhang, Y Chi, W Chen, TY Liu
IEEE Transactions on Signal Processing 68, 3976-3989, 2020
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20