arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02450math.OC
收藏

无投影动力学的分布式Optimization

Distributed Optimization with Projection-free Dynamics

Guanpu Chen, Peng Yi, Yiguang Hong, Jie Chen

摘要:

本文考虑了带集合约束的连续时间动态分布优化问题。为了解决基于投影的动力学求解一般二次优化子问题时的计算复杂性问题,我们采用Frank-Wolfe方法,也称为条件梯度算法,提出了一种分布式无投影动力学.该过程通过求解替代的线性最优化而不是二次优化来搜索可行的下降方向。为了使该方法适用于权重平衡的有向图,我们设计了一个动态的共识的局部决策变量和另一个动态的辅助变量跟踪全局梯度。然后,我们证明了动力系统的最优解的收敛性,并提供了详细的数值比较与基于投影的动力学和其他分布式投影自由算法。此外,我们推导出分布式离散时间计划的指导思想,建议的动力学,并提供相应的收敛速度。

英文摘要:

We consider continuous-time dynamics for distributed optimization with set constraints in the paper. To handle the computational complexity of projection-based dynamics due to solving a general quadratic optimization subproblem with projection, we propose a distributed projection-free dynamics by employing the Frank-Wolfe method, also known as the conditional gradient algorithm. The process searches a feasible descent direction by solving an alternative linear optimization instead of a quadratic one. To make the approach applicable over weight-balanced digraphs, we design a dynamics for the consensus of local decision variables and another dynamics of auxiliary variables to track the global gradient. Then we prove the convergence of the dynamical systems to the optimal solution, and provide detailed numerical comparisons with both projection-based dynamics and other distributed projection-free algorithms. Also, we derive the distributed discrete-time scheme following the instructive ideas of the proposed dynamics and provide its accordingly convergence rate.

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。

↑