arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.02271math.OC
收藏

时变网络上非光滑非凸优化的分布式邻近梯度算法

Distributed proximal gradient algorithm for non-smooth non-convex optimization over time-varying networks

Xia Jiang, Xianlin Zeng, Jian Sun, Jie Chen

摘要:

研究了具有非光滑正则化的分布式非凸优化问题,该问题在分散学习、估计和控制中有着广泛的应用。目标函数是不同的局部目标函数的和,这些局部目标函数由可微的(可能是非凸的)费用函数和非光滑的凸函数组成。针对时变多智能体网络上的非光滑非凸优化问题,提出了一种分布式近似梯度算法。每个智能体通过多步一致性算子和邻近算子更新局部变量估计。我们证明了生成的局部变量达到共识,收敛到一组临界点的收敛速度$O(1/T)$。最后,通过数值模拟验证了该算法的有效性.

英文摘要:

This note studies the distributed non-convex optimization problem with non-smooth regularization, which has wide applications in decentralized learning, estimation and control. The objective function is the sum of different local objective functions, which consist of differentiable (possibly non-convex) cost functions and non-smooth convex functions. This paper presents a distributed proximal gradient algorithm for the non-smooth non-convex optimization problem over time-varying multi-agent networks. Each agent updates local variable estimate by the multi-step consensus operator and the proximal operator. We prove that the generated local variables achieve consensus and converge to the set of critical points with convergence rate $O(1/T)$. Finally, we verify the efficacy of proposed algorithm by numerical simulations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑