Wei Hu

Citirano

	Sve	Od 2020.
Citati	5576	5219
H-indeks	25	25
i10-indeks	33	31

1300

650

325

975

20172018201920202021202220232024202519 47 272 674 907 999 1169 1279 189

Javni pristup

Prikaži sve

22 članka

0 članaka

dostupno

nije dostupno

Na temelju uvjeta financiranja

Suautori

Simon Shaolei DuAssistant Professor, School of Computer Science and Engineering, University of WashingtonPotvrđena adresa e-pošte na cs.washington.edu
Zhiyuan LiAssistant Professor, Toyota Technological Institute at ChicagoPotvrđena adresa e-pošte na ttic.edu
Sanjeev AroraProfessor of Computer Science, Princeton UniversityPotvrđena adresa e-pošte na princeton.edu
Ruosong WangAssistant Professor, Peking UniversityPotvrđena adresa e-pošte na pku.edu.cn
Jason D. LeeAssociate Professor of Electrical Engineering and Computer Science, Princeton UniversityPotvrđena adresa e-pošte na princeton.edu
Ruslan SalakhutdinovUPMC Professor, Machine Learning Department, CMUPotvrđena adresa e-pošte na cs.cmu.edu
Lechao XiaoGoogle DeepMindPotvrđena adresa e-pošte na google.com
Qi LeiAssistant Professor of Mathematics and Data Science, New York UniversityPotvrđena adresa e-pošte na nyu.edu
Yuping LuoComputer Science Department, Princeton UniversityPotvrđena adresa e-pošte na cs.princeton.edu
Jeffrey PenningtonGoogle BrainPotvrđena adresa e-pošte na google.com
Spencer FreiGoogle DeepMindPotvrđena adresa e-pošte na google.com
Gal VardiWeizmann Institute of SciencePotvrđena adresa e-pošte na weizmann.ac.il
Qing QuAssistant Professor, Dept. of EECS, University of MichiganPotvrđena adresa e-pošte na umich.edu
Noah GolowichMITPotvrđena adresa e-pošte na mit.edu
Sham M KakadeHarvard UniversityPotvrđena adresa e-pošte na seas.harvard.edu
Pravesh K. KothariPrinceton UniversityPotvrđena adresa e-pošte na cs.cmu.edu
Yongyi YangUniversity of MichiganPotvrđena adresa e-pošte na umich.edu
Jacob SteinhardtStanford UniversityPotvrđena adresa e-pošte na cs.stanford.edu
Elad HazanProfessor at Princeton University and Director Google AI PrincetonPotvrđena adresa e-pošte na princeton.edu
Yuanzhi LiAssistant Professor at CMUPotvrđena adresa e-pošte na andrew.cmu.edu

Prati

Wei Hu

Assistant Professor of Computer Science and Engineering, University of Michigan

Potvrđena adresa e-pošte na umich.edu - Početna stranica

Theoretical Machine Learning


Naslov Poredaj po navodima Poredaj po godini Poredaj po naslovu	Citirano Citirano	Godina
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	1144	2019
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	1063	2019
Implicit regularization in deep matrix factorization S Arora, N Cohen, W Hu, Y Luo Advances in neural information processing systems 32, 2019	617	2019
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	306	2018
Few-shot learning via learning the representation, provably SS Du, W Hu, SM Kakade, JD Lee, Q Lei arXiv preprint arXiv:2002.09434, 2020	292	2020
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	256	2018
An analysis of the t-sne algorithm for data visualization S Arora, W Hu, PK Kothari Conference on learning theory, 1455-1462, 2018	231	2018
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	165	2016
Provable benefit of orthogonal initialization in optimizing deep linear networks W Hu, L Xiao, J Pennington arXiv preprint arXiv:2001.05992, 2020	149	2020
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	145	2019
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	144	2019
Width provably matters in optimization for deep linear neural networks S Du, W Hu International Conference on Machine Learning, 1655-1664, 2019	103	2019
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	99	2019
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	93	2019
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	83	2022
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	80	2020
Impact of representation learning in linear bandits J Yang, W Hu, JD Lee, SS Du arXiv preprint arXiv:2010.06531, 2020	72*	2020
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	67	2017
How do transformers learn in-context beyond simple functions? a case study on learning with representations T Guo, W Hu, S Mei, H Wang, C Xiong, S Savarese, Y Bai arXiv preprint arXiv:2310.10616, 2023	58	2023
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	57	2022

Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.

Članci 1–20

Godišnji broj citata

Dvostruki navodi

Spojeni navodi

Dodavanje suautoraSuautori

Prati

Citirano

Suautori