An Optimization Framework for Federated Edge Learning

卡鲁什-库恩-塔克条件 计算机科学 数学优化 序列(生物学) 次梯度方法 最优化问题 算法 趋同(经济学) 数学 经济 生物 经济增长 遗传学
作者
Yangchen Li,Ying Cui,Vincent K. N. Lau
出处
期刊:IEEE Transactions on Wireless Communications [Institute of Electrical and Electronics Engineers]
卷期号:22 (2): 934-949 被引量:4
标识
DOI:10.1109/twc.2022.3199564
摘要

The optimal design of federated learning (FL) algorithms for solving general machine learning (ML) problems in practical edge computing systems with quantized message passing remains an open problem. This paper considers an edge computing system where the server and workers have possibly different computing and communication capabilities and employ quantization before transmitting messages. To explore the full potential of FL in such an edge computing system, we first present a general FL algorithm, namely GenQSGD, parameterized by the numbers of global and local iterations, mini-batch size, and step size sequence. Then, we analyze its convergence for an arbitrary step size sequence and specify the convergence results under three commonly adopted step size rules, namely the constant, exponential, and diminishing step size rules. Next, we optimize the algorithm parameters to minimize the energy cost under the time constraint and convergence error constraint, with the focus on the overall implementing process of FL. Specifically, for any given step size sequence under each considered step size rule, we optimize the numbers of global and local iterations and mini-batch size to optimally implement FL for applications with preset step size sequences. We also optimize the step size sequence along with these algorithm parameters to explore the full potential of FL. The resulting optimization problems are challenging non-convex problems with non-differentiable constraint functions. We propose iterative algorithms to obtain KKT points using general inner approximation (GIA) and tricks for solving complementary geometric programming (CGP). Finally, we numerically demonstrate the remarkable gains of GenQSGD with optimized algorithm parameters over existing FL algorithms and reveal the significance of optimally designing general FL algorithms.
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
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
YYMM发布了新的文献求助10
刚刚
刚刚
manforfull完成签到,获得积分10
1秒前
冰魂应助司徒寒烟采纳,获得10
2秒前
2秒前
Hello应助落后翠柏采纳,获得10
2秒前
幽梦挽歌发布了新的文献求助10
6秒前
7秒前
8秒前
萝卜干完成签到,获得积分10
8秒前
研友_VZG7GZ应助科研小助理采纳,获得10
9秒前
爆米花应助禾牧之采纳,获得10
10秒前
maxzplug发布了新的文献求助10
12秒前
鸿渊完成签到 ,获得积分10
15秒前
水水水水发布了新的文献求助10
16秒前
18秒前
今后应助兽先生采纳,获得10
18秒前
爱健身的小海豹完成签到,获得积分10
20秒前
鹭立江头完成签到,获得积分20
21秒前
酷波er应助青山采纳,获得10
23秒前
科研通AI2S应助sxc采纳,获得10
23秒前
bkagyin应助无奈的小松鼠采纳,获得10
24秒前
冰魂应助无奈的小松鼠采纳,获得10
24秒前
24秒前
五香发布了新的文献求助10
24秒前
Hello应助无奈的小松鼠采纳,获得100
24秒前
冰魂应助无奈的小松鼠采纳,获得10
24秒前
24秒前
Hello应助无奈的小松鼠采纳,获得10
24秒前
24秒前
冰魂应助无奈的小松鼠采纳,获得10
24秒前
24秒前
鹭立江头发布了新的文献求助10
24秒前
青梨完成签到 ,获得积分10
26秒前
27秒前
27秒前
悦耳娩完成签到,获得积分10
29秒前
大力哈密瓜完成签到 ,获得积分10
29秒前
29秒前
慕青应助蒋小亮采纳,获得10
30秒前
高分求助中
Encyclopedia of Mathematical Physics 2nd edition 888
Introduction to Strong Mixing Conditions Volumes 1-3 500
Tip60 complex regulates eggshell formation and oviposition in the white-backed planthopper, providing effective targets for pest control 400
Optical and electric properties of monocrystalline synthetic diamond irradiated by neutrons 320
共融服務學習指南 300
Essentials of Pharmacoeconomics: Health Economics and Outcomes Research 3rd Edition. by Karen Rascati 300
Peking Blues // Liao San 300
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3803508
求助须知:如何正确求助?哪些是违规求助? 3348396
关于积分的说明 10338293
捐赠科研通 3064441
什么是DOI,文献DOI怎么找? 1682571
邀请新用户注册赠送积分活动 808307
科研通“疑难数据库(出版商)”最低求助积分说明 764034