AI RESEARCH
High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking
arXiv CS.LG
•
ArXi:2605.00281v1 Announce Type: new We study high-probability (HP) convergence guarantees in decentralized stochastic optimization, where multiple agents collaborate to jointly train a model over a network. Existing HP results in decentralized settings almost exclusively focus on the Decentralized Stochastic Gradient Descent ($\mathtt{DSGD}$) algorithm, which requires strong assumptions, such as bounded data heterogeneity, or strong convexity of each agent's cost.