AI RESEARCH

Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation

arXiv CS.LG

ArXi:2605.19629v1 Announce Type: cross In this paper, we establish Berry-Esseen-type bounds for federated linear stochastic approximation (LSA). Our results provide the first federated Gaussian approximations for LSA that explicitly capture communication-computation trade-offs and heterogeneity-aware error terms, quantifying the effects of local step size, number of local updates, and heterogeneity on convergence rates.