One Gradient Frank-Wolfe for Decentralized Online Convex and Submodular Optimization
This addresses the problem of decentralized learning in dynamic data environments for applications like federated learning, though it is incremental as it extends existing offline methods to online settings.
The paper tackles decentralized online optimization for convex and continuous DR-submodular functions, achieving performance guarantees comparable to centralized offline methods while requiring only a single gradient computation per participant per time step, with competitive results in real-world experiments.
Decentralized learning has been studied intensively in recent years motivated by its wide applications in the context of federated learning. The majority of previous research focuses on the offline setting in which the objective function is static. However, the offline setting becomes unrealistic in numerous machine learning applications that witness the change of massive data. In this paper, we propose \emph{decentralized online} algorithm for convex and continuous DR-submodular optimization, two classes of functions that are present in a variety of machine learning problems. Our algorithms achieve performance guarantees comparable to those in the centralized offline setting. Moreover, on average, each participant performs only a \emph{single} gradient computation per time step. Subsequently, we extend our algorithms to the bandit setting. Finally, we illustrate the competitive performance of our algorithms in real-world experiments.