Zhiyuan Li

Cited by

	All	Since 2020
Citations	5384	5092
h-index	27	27
i10-index	34	34

1500

750

375

1125

20172018201920202021202220232024202514 34 234 637 788 985 1054 1459 162

Public access

View all

21 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Sanjeev AroraProfessor of Computer Science, Princeton UniversityVerified email at princeton.edu
Wei HuAssistant Professor of Computer Science and Engineering, University of MichiganVerified email at umich.edu
Simon Shaolei DuAssistant Professor, School of Computer Science and Engineering, University of WashingtonVerified email at cs.washington.edu
Ruosong WangAssistant Professor, Peking UniversityVerified email at pku.edu.cn
Kaifeng LyuPrinceton UniversityVerified email at princeton.edu
Tengyu MAStanford UniversityVerified email at stanford.edu
Ruslan SalakhutdinovUPMC Professor, Machine Learning Department, CMUVerified email at cs.cmu.edu
Dingli YuMicrosoft ResearchVerified email at microsoft.com
Srinadh BhojanapalliResearch Scientist, Google ResearchVerified email at google.com
Tianhao WangResearch Assistant Professor, Toyota Technological Institute at ChicagoVerified email at ttic.edu
Hong LiuStanford UniversityVerified email at stanford.edu
Kaiyue WenPhd Student, Stanford UniversityVerified email at stanford.edu
Yann LeCunChief AI Scientist at Facebook & Silver Professor at the Courant Institute, New York UniversityVerified email at cs.nyu.edu
Behnam NeyshaburMember of Technical Staff, AnthropicVerified email at anthropic.com
Nathan SrebroProfessor, TTIC and University of ChicagoVerified email at ttic.edu
Sadhika MalladiPrinceton UniversityVerified email at princeton.edu
Jason D. LeeAssociate Professor of Electrical Engineering and Computer Science, Princeton UniversityVerified email at princeton.edu
Yi ZhangSenior Researcher at Microsoft Research RedmondVerified email at microsoft.com
Percy LiangAssociate Professor of Computer Science, Stanford UniversityVerified email at cs.stanford.edu
David HallStanfordVerified email at stanford.edu

Zhiyuan Li

Assistant Professor, Toyota Technological Institute at Chicago

Verified email at ttic.edu - Homepage

deep learning theory machine learning theory


Title Sort by citations Sort by year Sort by 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	1124	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	1069	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	639	2018
An exponential learning rate schedule for deep learning Z Li, S Arora arXiv preprint arXiv:1910.07454, 2019	245	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	204	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	153	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	142	2019
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	132	2016
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	129	2023
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	118	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
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
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	92	2021
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	89	2021
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	83	2022
How Does Sharpness-Aware Minimization Minimizes Sharpness? K Wen, T Ma, Z Li The Eleventh International Conference on Learning Representations, 2023	82	2023
Chain of thought empowers transformers to solve inherently serial problems Z Li, H Liu, D Zhou, T Ma arXiv preprint arXiv:2402.12875, 2024	79	2024
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	79	2020

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors