Gradient-free distributed online optimization in networks
Yuhang Liu1
Wenxiao Zhao2
Nan Zhang1
Dongdong Lv1
Shuai Zhang1
1.Academy of Information and Communication Research,State Grid Information and Telecommunication Group Co.,Ltd.,Beijing 102211,China2.The Key Laboratory of Systems and Control,Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China;School of Mathematical Sciences,University of Chinese Academy of Sciences,Beijing 100049,China
摘要：In this paper,we consider the distributed online optimization problem on a time-varying network,where each agent on the network has its own time-varying objective function and the goal is to minimize the overall loss accumulated.Moreover,we focus on distributed algorithms which do not use gradient information and projection operators to improve the applicability and computational efficiency.By introducing the deterministic differences and the randomized differences to substitute the gradient information of the objective functions and removing the projection operator in the traditional algorithms,we design two kinds of gradient-free distributed online optimization algorithms without projection step,which can economize considerable computational resources as well as has less limitations on the applicability.We prove that both of two algorithms achieves consensus of the estimates and regrets of O(log(T))for local strongly convex objective,respectively.Finally,a simulation example is provided to verify the theoretical results.
机标关键词：optimizationdistributedonlinegradient-freenetworks
论文发表日期：2025-05-30
在线出版日期：2025-08-15（本平台首次上网日期，不代表文献的发表时间）
页数：14( 207-220 )
英文信息