首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Decentralized Stochastic Non-Convex Optimization over Weakly Connected Time-Varying Digraphs
【24h】

Decentralized Stochastic Non-Convex Optimization over Weakly Connected Time-Varying Digraphs

机译:分散的随机非凸优化弱连接时变形数字

获取原文

摘要

In this paper, we consider decentralized stochastic non-convex optimization over a class of weakly connected digraphs. First, we quantify the convergence behaviors of the weight matrices of this type of digraphs. By leveraging the perturbed push sum protocol and gradient tracking techniques, we propose a decentralized stochastic algorithm that is able to converge to the first-order stationary points of non-convex problems with provable convergence rates. Our digraph structure considered in this work generalizes the existing settings such that the proposed algorithm can be applied to more practical decentralized learning scenarios. Numerical results showcase the strengths of our theory and superiority of the proposed algorithm in decentralized training problems compared with the existing counterparts.
机译:在本文中,我们考虑了一类弱连接的上下层的随机非凸优化。 首先,我们量化这种类型的数字的权重矩阵的收敛行为。 通过利用扰动的推送和协议和梯度跟踪技术,我们提出了一种分散的随机算法,能够通过可提供可提供的收敛速率收敛到非凸面问题的一阶静止点。 我们在本工作中考虑的Digraph结构概括了现有的设置,使得所提出的算法可以应用于更实际的分散的学习场景。 与现有对应物相比,数值展示了我们在分散训练问题中提出的算法的理论和优越性的优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号