Kuangyu Ding

According to our database, Kuangyu Ding authored at least 8 papers between 2023 and 2025.

Collaborative distances:

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

2025

Stochastic Bregman Subgradient Methods for Nonsmooth Nonconvex Optimization Problems.

Kuangyu Ding, Kim-Chuan Toh

J. Optim. Theory Appl., September, 2025

On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem.

Kuangyu Ding, Kim-Chuan Toh

CoRR, July, 2025

Adam-family Methods with Decoupled Weight Decay in Deep Learning.

Kuangyu Ding, Nachuan Xiao, Kim-Chuan Toh

Trans. Mach. Learn. Res., 2025

2024

Memory-Efficient 4-bit Preconditioned Stochastic Optimization.

Jingyang Li, Kuangyu Ding, Kim-Chuan Toh, Pan Zhou

CoRR, 2024

Optimization Hyper-parameter Laws for Large Language Models.

Xingyu Xie, Kuangyu Ding, Shuicheng Yan, Kim-Chuan Toh, Tianwen Wei

CoRR, 2024

Developing Lagrangian-based Methods for Nonsmooth Nonconvex Optimization.

Nachuan Xiao, Kuangyu Ding, Xiaoyin Hu, Kim-Chuan Toh

CoRR, 2024

2023

On proximal augmented Lagrangian based decomposition methods for dual block-angular convex composite programming problems.

Kuangyu Ding, Xin Yee Lam, Kim-Chuan Toh

Comput. Optim. Appl., September, 2023

Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning.

Kuangyu Ding, Jingyang Li, Kim-Chuan Toh

CoRR, 2023