Push–Pull Gradient Methods for Distributed Optimization in Networks

八卦 数学优化 计算机科学 异步通信 分布式算法 凸函数 凸优化 节点(物理) 功能(生物学) 最优化问题 变量(数学) 信息交流 正多边形 分布式计算 数学 生物 进化生物学 工程类 社会心理学 数学分析 电信 结构工程 计算机网络 心理学 几何学
作者
Shi Pu,Wei Shi,Jinming Xu,Angelia Nedić
出处
期刊:IEEE Transactions on Automatic Control [Institute of Electrical and Electronics Engineers]
卷期号:66 (1): 1-16 被引量:260
标识
DOI:10.1109/tac.2020.2972824
摘要

In this article, we focus on solving a distributed convex optimization problem in a network, where each agent has its own convex cost function and the goal is to minimize the sum of the agents' cost functions while obeying the network connectivity structure. In order to minimize the sum of the cost functions, we consider new distributed gradient-based methods where each node maintains two estimates, namely an estimate of the optimal decision variable and an estimate of the gradient for the average of the agents' objective functions. From the viewpoint of an agent, the information about the gradients is pushed to the neighbors, whereas the information about the decision variable is pulled from the neighbors, hence giving the name "push-pull gradient methods." The methods utilize two different graphs for the information exchange among agents and, as such, unify the algorithms with different types of distributed architecture, including decentralized (peer to peer), centralized (master-slave), and semicentralized (leader-follower) architectures. We show that the proposed algorithms and their many variants converge linearly for strongly convex and smooth objective functions over a network (possibly with unidirectional data links) in both synchronous and asynchronous random-gossip settings. In particular, under the random-gossip setting, "push-pull" is the first class of algorithms for distributed optimization over directed graphs. Moreover, we numerically evaluate our proposed algorithms in both scenarios, and show that they outperform other existing linearly convergent schemes, especially for ill-conditioned problems and networks that are not well balanced.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
胡萝卜发布了新的文献求助10
1秒前
哈哈哈发布了新的文献求助10
2秒前
2秒前
汉堡包应助果粒多采纳,获得10
3秒前
7秒前
华仔发布了新的文献求助20
7秒前
7秒前
科研通AI2S应助杜杜采纳,获得10
9秒前
量子星尘发布了新的文献求助10
10秒前
JK发布了新的文献求助10
10秒前
打打应助顺利一德采纳,获得10
11秒前
法外狂徒完成签到,获得积分10
12秒前
Orange应助十九岁的时差采纳,获得10
12秒前
科研通AI2S应助steam采纳,获得10
14秒前
潇湘雪月发布了新的文献求助10
14秒前
15秒前
青青子衿完成签到,获得积分10
15秒前
15秒前
15秒前
17秒前
crazy发布了新的文献求助10
20秒前
杜杜发布了新的文献求助10
21秒前
嗯嗯发布了新的文献求助10
22秒前
老大蒂亚戈完成签到,获得积分10
24秒前
宝安完成签到,获得积分10
28秒前
JamesPei应助动听的老鼠采纳,获得10
28秒前
28秒前
杨可言完成签到,获得积分10
28秒前
29秒前
29秒前
30秒前
Hello应助子非鱼采纳,获得10
31秒前
32秒前
34秒前
mzhmhy发布了新的文献求助10
36秒前
李健的粉丝团团长应助ASA采纳,获得30
37秒前
Choi完成签到,获得积分0
37秒前
无辜如容发布了新的文献求助10
37秒前
123完成签到,获得积分10
38秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989263
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253814
捐赠科研通 3270066
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136