A weighted-sum scalarization of agent and coordinator objectives yields a FedAvg-like decentralized algorithm with O(1/sqrt(T)) convergence under convexity and bounded heterogeneity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Multi-Objective Optimization framework for Decentralized Learning with coordination constraints
A weighted-sum scalarization of agent and coordinator objectives yields a FedAvg-like decentralized algorithm with O(1/sqrt(T)) convergence under convexity and bounded heterogeneity.