arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09506cs.LGcs.CRcs.DC
收藏

基于小批量SSCA的样本联邦学习

Sample-based Federated Learning via Mini-batch SSCA

Shanghai Jiao Tong University(上海交通大学)

Chencheng Ye, Ying Cui

摘要:

在本文中,我们研究无约束和有约束的样本为基础的联邦优化,分别。对于每个问题,我们提出了一个隐私保护算法,使用随机逐次凸逼近(SSCA)技术,并证明它可以收敛到Karush-Kuhn-Tucker(KKT)点。据我们所知,SSCA还没有被用于解决联邦优化,和联邦优化与非凸约束尚未调查。接下来,我们自定义两个建议的基于SSCA的算法的两个应用程序的例子,并提供封闭形式的解决方案,为各自的近似凸问题在每次迭代的SSCA。最后,数值实验表明,所提出的算法在收敛速度,通信成本和模型规格方面的固有优势。

英文摘要:

In this paper, we investigate unconstrained and constrained sample-based federated optimization, respectively. For each problem, we propose a privacy preserving algorithm using stochastic successive convex approximation (SSCA) techniques, and show that it can converge to a Karush-Kuhn-Tucker (KKT) point. To the best of our knowledge, SSCA has not been used for solving federated optimization, and federated optimization with nonconvex constraints has not been investigated. Next, we customize the two proposed SSCA-based algorithms to two application examples, and provide closed-form solutions for the respective approximate convex problems at each iteration of SSCA. Finally, numerical experiments demonstrate inherent advantages of the proposed algorithms in terms of convergence speed, communication cost and model specification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑