DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime
This addresses a foundational challenge in federated learning for broader applicability, though it appears incremental in method.
The paper tackles the problem of communication acceleration in federated learning for general convex cost functions that may not be smooth nor strongly convex, achieving a solution to an open theoretical problem with detailed analysis for local iteration complexity.
We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.