English(EN) Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm

新算法解决联邦学习中的噪声问题 · 跟踪到1个来源

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-21 12:18

研究人员开发了一种名为VRA-FedSGD的新算法，以改善在存在显著噪声的联邦学习场景。该算法旨在处理大规模机器学习应用中常见的重尾梯度噪声和通信噪声，尤其是在涉及物联网的应用中。VRA-FedSGD利用动量方差缩减和非线性映射技术来减轻噪声，并在模拟中针对各种目标函数展示了有效的收敛速率。 AI

影响该算法可以提高在嘈杂环境中分布式机器学习模型的可靠性和效率。

排序理由该集群包含一篇详细介绍联邦学习新算法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Zahra Kharaghani, Ali Dadras, Tommy L\"ofstedt · 2026-06-24 04:00

FAIRVAR: Fair Federated Learning via Variance Regularization

arXiv:2508.12042v3 Announce Type: replace Abstract: Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the glob…
arXiv cs.LG TIER_1 English(EN) · Yongchao Liu · 2026-06-21 12:18

具有重尾梯度噪声和通信噪声的联邦学习：一种方差缩减算法

Federated learning (FL) is an emerging distributed machine learning paradigm that enables local devices to jointly train a global model while keeping data decentralized and private. We propose a variance-reduction based algorithm, VRA-FedSGD, for FL in the presence of heavy-taile…