期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 9, 页码 6568-6577出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3127883
关键词
Optimization; Dynamical systems; Machine learning; Damping; Convergence; Convex functions; Linear programming; Distributed optimization; machine learning; Nesterov accelerated system; projected primal-dual method; second-order dynamical system
This article focuses on developing distributed optimization strategies for a class of machine learning problems over a directed network of computing agents. By introducing a second-order Nesterov accelerated dynamical system and the projected primal-dual method, the constraints in the problems are effectively dealt with, and the theoretical results are validated by practical problems.
This article focuses on developing distributed optimization strategies for a class of machine learning problems over a directed network of computing agents. In these problems, the global objective function is an addition function, which is composed of local objective functions. Such local objective functions are convex and only endowed by the corresponding computing agent. A second-order Nesterov accelerated dynamical system with time-varying damping coefficient is developed to address such problems. To effectively deal with the constraints in the problems, the projected primal-dual method is carried out in the Nesterov accelerated system. By means of the cocoercive maximal monotone operator, it is shown that the trajectories of the Nesterov accelerated dynamical system can reach consensus at the optimal solution, provided that the damping coefficient and gains meet technical conditions. In the end, the validation of the theoretical results is demonstrated by the email classification problem and the logistic regression problem in machine learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据