7 citations · 7 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Convergence of Spectral Descent for Non-smooth Optimization
Yixuan Yang, Yuqing He, Song Li
The Muon optimizer has recently demonstrated remarkable empirical success in training large language models. However, the theoretical understanding of its mechanisms remains limite…
cs.LG2021★ 7 cited
Dynamic Differential-Privacy Preserving SGD
Jian Du, Song Li, Xiangyi Chen +2
The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privac…