Convergence analysis for multiple stale-neighbor local steps
Establish a convergence guarantee for the projected-gradient GTVMin algorithm when each communication round performs more than one local update using stale neighbor parameters.
References
For $T_{\mathrm{loc}}>1$, later local steps use stale neighbor parameters; the $T_{\mathrm{loc}}=5$ used in the experiments is a communication-saving heuristic, also open.
— Federated Soft Clustering via Generalized Total Variation Minimization
(2609.19202 - Abdurakhmanova et al., 16 Sep 2026) in Section 3, “Algorithm and Convergence”