Distributed empirical risk minimization over directed graphs
2019 53rd Asilomar Conference on Signals, Systems, and Computers(2019)
摘要
In this paper, we present stochastic optimization for empirical risk minimization over directed graphs. Using a novel information fusion approach that utilizes both row- and column-stochastic weights simultaneously, we propose SAB, a decentralized stochastic gradient method with gradient tracking, and show that the proposed algorithm converges linearly to an error ball around the optimal solution with a constant step-size. We provide a sketch of the convergence analysis as well as the generalization of the proposed algorithm. Finally, we illustrate the theoretical results with the help of experiments with real data.
更多查看译文
关键词
Stochastic optimization,Decentralized algorithms,multi-agent systems,directed graphs
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络