Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training

NeurIPSSpotlight2025

Authors
Qinglun Li, Yingqi Liu, Miao Zhang, Xiaochun Cao, Quanjun Yin, Li Shen
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Decentralized training removes the centralized server, making it a communication-efficient approach that can significantly improve training efficiency, but it often suffers from degraded performance c…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

generalization efficient

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive