Zhiyuan Li

Navedeno

	Vse	Od leta 2020
Navedbe	5507	5215
indeks h	28	28
indeks i10	35	35

1400

700

350

1050

20172018201920202021202220232024202514 34 230 639 787 986 1163 1347 286

Javni dostop

Prikaži vse

22 člankov

0 člankov

na voljo

ni na voljo

Na podlagi zahtev v povezavi s financiranjem

Soavtorji

Sanjeev AroraProfessor of Computer Science, Princeton UniversityPreverjeni e-poštni naslov na princeton.edu
Wei HuAssistant Professor of Computer Science and Engineering, University of MichiganPreverjeni e-poštni naslov na umich.edu
Simon Shaolei DuAssistant Professor, School of Computer Science and Engineering, University of WashingtonPreverjeni e-poštni naslov na cs.washington.edu
Ruosong WangAssistant Professor, Peking UniversityPreverjeni e-poštni naslov na pku.edu.cn
Kaifeng LyuPrinceton UniversityPreverjeni e-poštni naslov na princeton.edu
Tengyu MAStanford UniversityPreverjeni e-poštni naslov na stanford.edu
Ruslan SalakhutdinovUPMC Professor, Machine Learning Department, CMUPreverjeni e-poštni naslov na cs.cmu.edu
Dingli YuMicrosoft ResearchPreverjeni e-poštni naslov na microsoft.com
Srinadh BhojanapalliResearch Scientist, Google ResearchPreverjeni e-poštni naslov na google.com
Hong LiuStanford UniversityPreverjeni e-poštni naslov na stanford.edu
Tianhao WangResearch Assistant Professor, Toyota Technological Institute at ChicagoPreverjeni e-poštni naslov na ttic.edu
Kaiyue WenPhd Student, Stanford UniversityPreverjeni e-poštni naslov na stanford.edu
Yann LeCunChief AI Scientist at Facebook & JT Schwarz Professor at the Courant Institute, New York UniversityPreverjeni e-poštni naslov na cs.nyu.edu
Behnam NeyshaburMember of Technical Staff, AnthropicPreverjeni e-poštni naslov na anthropic.com
Nathan SrebroProfessor, TTIC and University of ChicagoPreverjeni e-poštni naslov na ttic.edu
Jason D. LeeAssociate Professor of Electrical Engineering and Computer Science, Princeton UniversityPreverjeni e-poštni naslov na princeton.edu
Yi ZhangSenior Researcher at Microsoft Research RedmondPreverjeni e-poštni naslov na microsoft.com
Percy LiangAssociate Professor of Computer Science, Stanford UniversityPreverjeni e-poštni naslov na cs.stanford.edu
David HallStanfordPreverjeni e-poštni naslov na stanford.edu
Sadhika MalladiPrinceton UniversityPreverjeni e-poštni naslov na princeton.edu

Spremljaj

Zhiyuan Li

Assistant Professor, Toyota Technological Institute at Chicago

Preverjeni e-poštni naslov na ttic.edu - Domača stran

deep learning theory machine learning theory


Naslov Razvrsti po navedbah Razvrsti po letniku Razvrsti po naslovu	Navedeno Navedeno	Leto
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	1148	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	1076	2019
Towards understanding the role of over-parametrization in generalization of neural networks B Neyshabur, Z Li, S Bhojanapalli, Y LeCun, N Srebro arXiv preprint arXiv:1805.12076, 2018	654	2018
An exponential learning rate schedule for deep learning Z Li, S Arora arXiv preprint arXiv:1910.07454, 2019	251	2019
Harnessing the power of infinitely wide deep nets on small-data tasks S Arora, SS Du, Z Li, R Salakhutdinov, R Wang, D Yu	206	2019
Towards resolving the implicit bias of gradient descent for matrix factorization: Greedy low-rank learning Z Li, Y Luo, K Lyu arXiv preprint arXiv:2012.09839, 2020	151	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
Sophia: A scalable stochastic second-order optimizer for language model pre-training H Liu, Z Li, D Hall, P Liang, T Ma arXiv preprint arXiv:2305.14342, 2023	141	2023
Theoretical analysis of auto rate-tuning by batch normalization S Arora, Z Li, K Lyu arXiv preprint arXiv:1812.03981, 2018	133	2018
Learning in games: Robustness of fast convergence DJ Foster, Z Li, T Lykouris, K Sridharan, E Tardos Advances in Neural Information Processing Systems 29, 2016	131	2016
Understanding gradient descent on the edge of stability in deep learning S Arora, Z Li, A Panigrahi International Conference on Machine Learning, 948-1024, 2022	121	2022
What Happens after SGD Reaches Zero Loss?--A Mathematical Framework Z Li, T Wang, S Arora arXiv preprint arXiv:2110.06914, 2021	114	2021
Simple and effective regularization methods for training on noisily labeled data with generalization guarantee W Hu, Z Li, D Yu International Conference on Learning Representations (ICLR 2020), 2019	102*	2019
On the validity of modeling sgd with stochastic differential equations (sdes) Z Li, S Malladi, S Arora Advances in Neural Information Processing Systems 34, 12712-12725, 2021	100	2021
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	100	2019
Gradient descent on two-layer nets: Margin maximization and simplicity bias K Lyu, Z Li, R Wang, S Arora Advances in Neural Information Processing Systems 34, 12978-12991, 2021	96	2021
Chain of thought empowers transformers to solve inherently serial problems Z Li, H Liu, D Zhou, T Ma arXiv preprint arXiv:2402.12875 1, 2024	92	2024
How Does Sharpness-Aware Minimization Minimizes Sharpness? K Wen, T Ma, Z Li The Eleventh International Conference on Learning Representations, 2023	89	2023
Understanding the generalization benefit of normalization layers: Sharpness reduction K Lyu, Z Li, S Arora Advances in Neural Information Processing Systems 35, 34689-34708, 2022	85	2022
Reconciling modern deep learning with traditional optimization analyses: The intrinsic learning rate Z Li, K Lyu, S Arora Advances in Neural Information Processing Systems 33, 14544-14555, 2020	81	2020

Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.

Članki 1–20

Št. navedb na leto

Podvojene navedbe

Združene navedbe

Dodajanje soavtorjevSoavtorji

Spremljaj

Navedeno

Soavtorji