AI RESEARCH
High-probability Convergence Guarantees of Decentralized SGD
arXiv CS.LG
•
ArXi:2510.06141v4 Announce Type: replace Convergence in high-probability (HP) has attracted increasing interest, due to implying exponentially decaying tail bounds and strong guarantees for individual runs of an algorithm. While many works study HP guarantees in centralized settings, much less is understood in the decentralized setup, where existing works require strong assumptions, like uniformly bounded gradients, or asymptotically vanishing noise.