Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Mingze Wang
Observed name:
Wang, Mingze
Institution:
Peking University
Observed institution:
Peking University
OpenAlex ID:
A5041887782
Generalization Error Bounds for Deep Neural Networks Trained by SGD
2022
·
Wang, Mingze
, Ma, Chao
·
arXiv (Cornell University)
·
3
PDF
Improving Generalization and Convergence by Enhancing Implicit Regularization
2024
·
Mingze Wang
, Jinbo Wang
, et al.
·
neural information processing systems
·
2
PDF
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
2024
·
Liu Ziyin
, Mingze Wang
, et al.
·
neural information processing systems
·
1
PDF
Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining
2026
·
Zhu, Shuchen
, Fang, Yuxin
, et al.
·
arXiv (Cornell University)
PDF
Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
2026
·
Zhu, Shuchen
, Hu, Rizhen
, et al.
·
arXiv (Cornell University)
PDF
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
2023
·
Wang, Mingze
, Min, Zeping
, et al.
·
arXiv (Cornell University)
PDF
A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent
2023
·
Wang, Mingze
, Wu, Lei
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
7
Citation count:
6
H-index:
2
I10-index:
Year
Topic
Type
