通过平均梯度流进行黎曼联盟学习

Zhenwei Huang, Wen Huang, Pratik Jawanpuria, Bamdev Mishra
{"title":"通过平均梯度流进行黎曼联盟学习","authors":"Zhenwei Huang, Wen Huang, Pratik Jawanpuria, Bamdev Mishra","doi":"arxiv-2409.07223","DOIUrl":null,"url":null,"abstract":"In recent years, federated learning has garnered significant attention as an\nefficient and privacy-preserving distributed learning paradigm. In the\nEuclidean setting, Federated Averaging (FedAvg) and its variants are a class of\nefficient algorithms for expected (empirical) risk minimization. This paper\ndevelops and analyzes a Riemannian Federated Averaging Gradient Stream\n(RFedAGS) algorithm, which is a generalization of FedAvg, to problems defined\non a Riemannian manifold. Under standard assumptions, the convergence rate of\nRFedAGS with fixed step sizes is proven to be sublinear for an approximate\nstationary solution. If decaying step sizes are used, the global convergence is\nestablished. Furthermore, assuming that the objective obeys the Riemannian\nPolyak-{\\L}ojasiewicz property, the optimal gaps generated by RFedAGS with\nfixed step size are linearly decreasing up to a tiny upper bound, meanwhile, if\ndecaying step sizes are used, then the gaps sublinearly vanish. Numerical simulations conducted on synthetic and real-world data demonstrate\nthe performance of the proposed RFedAGS.","PeriodicalId":501286,"journal":{"name":"arXiv - MATH - Optimization and Control","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Riemannian Federated Learning via Averaging Gradient Stream\",\"authors\":\"Zhenwei Huang, Wen Huang, Pratik Jawanpuria, Bamdev Mishra\",\"doi\":\"arxiv-2409.07223\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, federated learning has garnered significant attention as an\\nefficient and privacy-preserving distributed learning paradigm. In the\\nEuclidean setting, Federated Averaging (FedAvg) and its variants are a class of\\nefficient algorithms for expected (empirical) risk minimization. This paper\\ndevelops and analyzes a Riemannian Federated Averaging Gradient Stream\\n(RFedAGS) algorithm, which is a generalization of FedAvg, to problems defined\\non a Riemannian manifold. Under standard assumptions, the convergence rate of\\nRFedAGS with fixed step sizes is proven to be sublinear for an approximate\\nstationary solution. If decaying step sizes are used, the global convergence is\\nestablished. Furthermore, assuming that the objective obeys the Riemannian\\nPolyak-{\\\\L}ojasiewicz property, the optimal gaps generated by RFedAGS with\\nfixed step size are linearly decreasing up to a tiny upper bound, meanwhile, if\\ndecaying step sizes are used, then the gaps sublinearly vanish. Numerical simulations conducted on synthetic and real-world data demonstrate\\nthe performance of the proposed RFedAGS.\",\"PeriodicalId\":501286,\"journal\":{\"name\":\"arXiv - MATH - Optimization and Control\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Optimization and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07223\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Optimization and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07223","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

近年来,联合学习作为一种高效且保护隐私的分布式学习范例,受到了广泛关注。在欧几里得环境中,联合平均(FedAvg)及其变体是一类高效的预期(经验)风险最小化算法。本文开发并分析了一种黎曼联邦平均梯度流算法(RFedAGS),它是 FedAvg 的广义化,适用于在黎曼流形上定义的问题。在标准假设条件下,RFedAGS 的收敛速率(步长固定)被证明是近似静态解的亚线性收敛速率。如果使用衰减步长,则全局收敛是确定的。此外,假定目标服从 RiemannianPolyak-{L}ojasiewicz 特性,固定步长的 RFedAGS 所产生的最优间隙在一个很小的上限内是线性递减的,同时,如果使用衰减步长,那么间隙会亚线性地消失。在合成数据和实际数据上进行的数值模拟证明了所提出的 RFedAGS 的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Riemannian Federated Learning via Averaging Gradient Stream
In recent years, federated learning has garnered significant attention as an efficient and privacy-preserving distributed learning paradigm. In the Euclidean setting, Federated Averaging (FedAvg) and its variants are a class of efficient algorithms for expected (empirical) risk minimization. This paper develops and analyzes a Riemannian Federated Averaging Gradient Stream (RFedAGS) algorithm, which is a generalization of FedAvg, to problems defined on a Riemannian manifold. Under standard assumptions, the convergence rate of RFedAGS with fixed step sizes is proven to be sublinear for an approximate stationary solution. If decaying step sizes are used, the global convergence is established. Furthermore, assuming that the objective obeys the Riemannian Polyak-{\L}ojasiewicz property, the optimal gaps generated by RFedAGS with fixed step size are linearly decreasing up to a tiny upper bound, meanwhile, if decaying step sizes are used, then the gaps sublinearly vanish. Numerical simulations conducted on synthetic and real-world data demonstrate the performance of the proposed RFedAGS.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Trading with propagators and constraints: applications to optimal execution and battery storage Upgrading edges in the maximal covering location problem Minmax regret maximal covering location problems with edge demands Parametric Shape Optimization of Flagellated Micro-Swimmers Using Bayesian Techniques Rapid and finite-time boundary stabilization of a KdV system
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1