Distributed Learning with Convex SUM-of -Non-Convex Objective

Mengfei Zhang, Jie Chen, Cedric Richard

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Recent research works have shown that some classical optimization methods originally designed for dealing with convex problems can demonstrate similar properties when applied to non-convex scenar-ios, where the problems are both locally and globally non-convex. This has led to the widespread development of distributed strategies for non-convex problems. When the sum of the local non-convex costs remains (strongly) convex and the individual local costs are smooth, it indicates a specific scenario that has notable applications and can benefit from existing solving methods. In this paper, drawing inspiration from the efficiency and stability of diffusion adaptation, we explore the minimization of a strongly convex sum of non-convex local costs. Specifically, we provide an analysis to demonstrate the convergence behavior of the network. Simulations are conducted to validate our theory.

源语言英语
主期刊名2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
出版商Institute of Electrical and Electronics Engineers Inc.
36-40
页数5
ISBN(电子版)9798350344523
DOI
出版状态已出版 - 2023
活动9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023 - Herradura, 哥斯达黎加
期限: 10 12月 202313 12月 2023

出版系列

姓名2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023

会议

会议9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
国家/地区哥斯达黎加
Herradura
时期10/12/2313/12/23

指纹

探究 'Distributed Learning with Convex SUM-of -Non-Convex Objective' 的科研主题。它们共同构成独一无二的指纹。

引用此