Follow
Wei Hu
Wei Hu
Assistant Professor of Computer Science and Engineering, University of Michigan
Verified email at umich.edu - Homepage
Title
Cited by
Cited by
Year
Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks
S Arora, S Du, W Hu, Z Li, R Wang
International Conference on Machine Learning, 322-332, 2019
10902019
On exact computation with an infinitely wide neural net
S Arora, SS Du, W Hu, Z Li, RR Salakhutdinov, R Wang
Advances in neural information processing systems 32, 2019
10232019
Implicit regularization in deep matrix factorization
S Arora, N Cohen, W Hu, Y Luo
Advances in Neural Information Processing Systems 32, 2019
5852019
A convergence analysis of gradient descent for deep linear neural networks
S Arora, N Cohen, N Golowich, W Hu
arXiv preprint arXiv:1810.02281, 2018
2912018
Few-shot learning via learning the representation, provably
SS Du, W Hu, SM Kakade, JD Lee, Q Lei
arXiv preprint arXiv:2002.09434, 2020
2822020
Algorithmic regularization in learning deep homogeneous models: Layers are automatically balanced
SS Du, W Hu, JD Lee
Advances in neural information processing systems 31, 2018
2372018
An analysis of the t-sne algorithm for data visualization
S Arora, W Hu, PK Kothari
Conference on learning theory, 1455-1462, 2018
2132018
Combinatorial multi-armed bandit with general reward functions
W Chen, W Hu, F Li, J Li, Y Liu, P Lu
Advances in Neural Information Processing Systems 29, 2016
1582016
Provable benefit of orthogonal initialization in optimizing deep linear networks
W Hu, L Xiao, J Pennington
arXiv preprint arXiv:2001.05992, 2020
1422020
Linear convergence of the primal-dual gradient method for convex-concave saddle point problems without strong convexity
SS Du, W Hu
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
1422019
Enhanced convolutional neural tangent kernels
Z Li, R Wang, D Yu, SS Du, W Hu, R Salakhutdinov, S Arora
arXiv preprint arXiv:1911.00809, 2019
1382019
Width provably matters in optimization for deep linear neural networks
S Du, W Hu
International Conference on Machine Learning, 1655-1664, 2019
1012019
Explaining landscape connectivity of low-cost solutions for multilayer nets
R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, R Ge, S Arora
Advances in neural information processing systems 32, 2019
962019
Simple and effective regularization methods for training on noisily labeled data with generalization guarantee
W Hu, Z Li, D Yu
arXiv preprint arXiv:1905.11368, 2019
912019
The surprising simplicity of the early-time learning dynamics of neural networks
W Hu, L Xiao, B Adlam, J Pennington
Advances in Neural Information Processing Systems 33, 17116-17128, 2020
782020
More than a toy: Random matrix models predict how real-world neural representations generalize
A Wei, W Hu, J Steinhardt
International Conference on Machine Learning, 23549-23588, 2022
732022
Linear convergence of a frank-wolfe type algorithm over trace-norm balls
Z Allen-Zhu, E Hazan, W Hu, Y Li
Advances in neural information processing systems 30, 2017
652017
Impact of representation learning in linear bandits
J Yang, W Hu, JD Lee, SS Du
arXiv preprint arXiv:2010.06531, 2020
64*2020
Implicit bias in leaky relu networks trained on high-dimensional data
S Frei, G Vardi, PL Bartlett, N Srebro, W Hu
arXiv preprint arXiv:2210.07082, 2022
492022
New characterizations in turnstile streams with applications
Y Ai, W Hu, Y Li, DP Woodruff
31st Conference on Computational Complexity (CCC 2016), 2016
462016
The system can't perform the operation now. Try again later.
Articles 1–20