当前位置: X-MOL 学术IEEE Trans. Autom. Control › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dual Averaging Push for Distributed Convex Optimization Over Time-Varying Directed Graph
IEEE Transactions on Automatic Control ( IF 6.2 ) Pub Date : 8-9-2019 , DOI: 10.1109/tac.2019.2934216
Shu Liang , Le Yi Wang , George Yin

Inspired by the subgradient push method developed recently by Nedi_ et al. we present a distributed dual averaging push algorithm for constrained nonsmooth convex optimization over time-varying directed graph. Our algorithm combines the dual averaging method with the push-sum technique and achieves an O(1/ √k) convergence rate. Compared with the subgradient push algorithm, our algorithm, first, addresses the constrained problems, and, second, has a faster convergence rate, and, third, simplifies the convergence analysis. We also generalize the proposed algorithm so that input variables of subgradient oracles have guaranteed convergence.

中文翻译:


时变有向图上分布式凸优化的双平均推动



受到 Nedi_ 等人最近开发的次梯度推动方法的启发。我们提出了一种分布式对偶平均推送算法,用于时变有向图上的约束非光滑凸优化。我们的算法将对偶平均方法与推和技术相结合,并实现了 O(1/√k) 收敛速度。与次梯度推送算法相比,我们的算法首先解决了约束问题,其次具有更快的收敛速度,第三简化了收敛分析。我们还推广了所提出的算法,以便次梯度预言的输入变量保证收敛。
更新日期:2024-08-22
down
wechat
bug