PulseAugur
EN
LIVE 13:38:21

New algorithm tackles noise in federated learning · 1 source tracked

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new algorithm called VRA-FedSGD to improve federated learning in scenarios with significant noise. This algorithm is designed to handle both heavy-tailed gradient noise and communication noise, which are common in large-scale machine learning applications, particularly those involving the Internet of Things. VRA-FedSGD utilizes momentum variance reduction and nonlinear mapping techniques to mitigate noise and has demonstrated effective convergence rates in simulations for various objective functions. AI

IMPACT This algorithm could improve the reliability and efficiency of distributed machine learning models in noisy environments.

RANK_REASON The cluster contains an academic paper detailing a new algorithm for federated learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New algorithm tackles noise in federated learning · 1 source tracked

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Zahra Kharaghani, Ali Dadras, Tommy L\"ofstedt ·

    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…

  2. arXiv cs.LG TIER_1 English(EN) · Yongchao Liu ·

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

    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…

RELATED ENTITIES

RELATED TOPICS