Distributed regularized online optimization using forward-backward splitting
Deming Yuan1
Baoyong Zhang1
Shengyuan Xu1
Huanyu Zhao2
1.School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China2.Faculty of Automation,Huaiyin Institute of Technology,Huai'an 223003,China
摘要：This paper considers the problem of distributed online regularized optimization over a network that consists of multiple interacting nodes.Each node is endowed with a sequence of loss functions that are time-varying and a regularization function that is fixed over time.A distributed forward-backward splitting algorithm is proposed for solving this problem and both fixed and adaptive learning rates are adopted.For both cases,we show that the regret upper bounds scale as O(√T),where T is the time horizon.In particular,those rates match the centralized counterpart.Finally,we show the effectiveness of the proposed algorithms over an online distributed regularized linear regression problem.
机标关键词：distributedoptimizationforwardonlinebackwardregularizedsplittingusing
论文发表日期：2023-05-05
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：10( 212-221 )
英文信息