Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2020 · 10 citations · 0 references
ComputingComputer ScienceDistributed SystemsMachine LearningOptimizationCommunication ComplexityDecentralized ControlDistributed AlgorithmsDistributed ComputingNeural NetworksOptimization For Machine LearningComposite OptimizationComputational Complexity Of AlgorithmsDecentralized LearningDistributed OptimizationGradient DescentOptimization AlgorithmsProximal AlgorithmsRegularization
Decentralized optimization has wide applications in machine learning, signal processing, and control. In this paper, we study the decentralized composite optimization problem with a non-smooth regularization term. Many proximal gradient based decentralized algorithms have been proposed in the past. However, these algorithms do not achieve near optimal computational complexity and communication complexity. In this paper, we propose a new method which establishes the optimal computational complexity and a near optimal communication complexity. Our empirical study shows that the proposed algorithm outperforms existing state-of-the-art algorithms. © 2020 Neural information processing systems foundation. All rights reserved.