Dawei Li

According to our database, Dawei Li authored at least 10 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization.

Chung-Yiu Yau, Dawei Li, Athanasios Glentis, Valentyn Boreiko, Hoi-To Wai, Mingyi Hong

CoRR, May, 2026

Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates.

Athanasios Glentis, Dawei Li, Chung-Yiu Yau, Mingyi Hong

CoRR, May, 2026

2023

NTK-SAP: Improving neural network pruning by aligning training dynamics.

Yite Wang, Dawei Li, Ruoyu Sun

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Suboptimal Local Minima Exist for Wide Neural Networks with Smooth Activations.

Tian Ding, Dawei Li, Ruoyu Sun

Math. Oper. Res., November, 2022

On the Benefit of Width for Neural Networks: Disappearance of Basins.

Dawei Li, Tian Ding, Ruoyu Sun

SIAM J. Optim., September, 2022

2021

On a Faster R-Linear Convergence Rate of the Barzilai-Borwein Method.

Dawei Li, Ruoyu Sun

CoRR, 2021

RMSprop converges with proper hyper-parameter.

Naichen Shi, Dawei Li, Mingyi Hong, Ruoyu Sun

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

The Global Landscape of Neural Networks: An Overview.

Ruoyu Sun, Dawei Li, Shiyu Liang, Tian Ding, Rayadurgam Srikant

IEEE Signal Process. Mag., 2020

2019

Sub-Optimal Local Minima Exist for Almost All Over-parameterized Neural Networks.

Tian Ding, Dawei Li, Ruoyu Sun

CoRR, 2019

2018

Over-Parameterized Deep Neural Networks Have No Strict Local Minima For Any Continuous Activations.

Dawei Li, Tian Ding, Ruoyu Sun

CoRR, 2018