English(EN) On Federated Averaging with Partial Participation under a General Variance Condition

联邦平均收敛性在无BGD假设下得到分析

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

本文在一般方差条件下分析了部分参与的联邦平均（FedAvg）的收敛性。作者为光滑的非凸目标建立了有限时间平稳性界限，该界限显示了采样客户数量的线性加速。他们的结果不需要额外的数据异质性假设，如边界梯度差异性（BGD），并通过一个违反BGD但被其分析所涵盖的例子证明了其重要性。 AI

影响为分布式机器学习优化技术提供了理论进展。

排序理由关于优化算法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 37 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于优化算法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Ziming Wang, Kun Huang, Karl Henrik Johansson, Shi Pu · 2026-11-11 05:00

关于一般方差条件下部分参与的联邦平均

arXiv:2611.14239v1 Announce Type: cross Abstract: In this paper, we study the convergence of Federated Averaging (FedAvg) with partial participation under a general variance condition. In each communication round, the server samples $S$ of the $n$ clients uniformly at random with…