Showing math.OCShow all
2 papers · 1 filter
math.OC2026
Improved Convergence for Decentralized Stochastic Optimization with Biased Gradients
Qing Xu, Yiwei Liao, Wenqi Fan +2
Decentralized stochastic optimization has emerged as a fundamental paradigm for large-scale machine learning. However, practical implementations often rely on biased gradient estim…
math.OC2026
Stochastic Momentum Tracking Push-Pull for Decentralized Optimization over Directed Graphs
Wenqi Fan, Yiwei Liao, Qing Xu +2
Decentralized optimization over directed networks is frequently challenged by asymmetric communication and the inherent high variance of stochastic gradients, which collectively ca…