Wei Hu
Wei Hu
Verified email at princeton.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
3412019
On exact computation with an infinitely wide neural net
S Arora, SS Du, W Hu, Z Li, R Salakhutdinov, R Wang
arXiv preprint arXiv:1904.11955, 2019
2732019
Implicit regularization in deep matrix factorization
S Arora, N Cohen, W Hu, Y Luo
arXiv preprint arXiv:1905.13655, 2019
1102019
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
1002018
Algorithmic regularization in learning deep homogeneous models: Layers are automatically balanced
SS Du, W Hu, JD Lee
arXiv preprint arXiv:1806.00900, 2018
712018
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
632019
Combinatorial multi-armed bandit with general reward functions
W Chen, W Hu, F Li, J Li, Y Liu, P Lu
arXiv preprint arXiv:1610.06603, 2016
632016
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
422019
Linear convergence of a frank-wolfe type algorithm over trace-norm balls
Z Allen-Zhu, E Hazan, W Hu, Y Li
arXiv preprint arXiv:1708.02105, 2017
342017
Width provably matters in optimization for deep linear neural networks
S Du, W Hu
International Conference on Machine Learning, 1655-1664, 2019
322019
An analysis of the t-sne algorithm for data visualization
S Arora, W Hu, PK Kothari
Conference on Learning Theory, 1455-1462, 2018
302018
Explaining landscape connectivity of low-cost solutions for multilayer nets
R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, S Arora, R Ge
arXiv preprint arXiv:1906.06247, 2019
272019
New characterizations in turnstile streams with applications
Y Ai, W Hu, Y Li, DP Woodruff
31st Conference on Computational Complexity (CCC 2016), 2016
272016
Few-shot learning via learning the representation, provably
SS Du, W Hu, SM Kakade, JD Lee, Q Lei
arXiv preprint arXiv:2002.09434, 2020
252020
Provable benefit of orthogonal initialization in optimizing deep linear networks
W Hu, L Xiao, J Pennington
arXiv preprint arXiv:2001.05992, 2020
222020
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
19*2019
Online improper learning with an approximation oracle
E Hazan, W Hu, Y Li, Z Li
arXiv preprint arXiv:1804.07837, 2018
92018
Accurate and efficient indoor location by dynamic warping in sequence-type radio-map
X Ye, Y Wang, Y Guo, W Hu, D Li
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous …, 2018
52018
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
W Hu, L Xiao, B Adlam, J Pennington
arXiv preprint arXiv:2006.14599, 2020
22020
Nearly Optimal Dynamic -Means Clustering for High-Dimensional Data
W Hu, Z Song, LF Yang, P Zhong
arXiv preprint arXiv:1802.00459, 2018
22018
The system can't perform the operation now. Try again later.
Articles 1–20