2 papers
cs.LG2026
Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints
Shengping Xie, Zekun Wu, Quan Chen +1
Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normali…
math.OC2025
From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees
Shengping Xie, Chuyan Chen, Kun Yuan
Low-rank gradient compression methods, such as PowerSGD, have gained attention in communication-efficient distributed optimization. However, the convergence guarantees of PowerSGD…