Almanac
technique

gradient compression

techniqueactiveprovisionalgradient-compression-26e13e48·1 events·first seen 16d ago

Aliases: gradient compression

Co-occurring entities

More like this (12)

Recent events (1)

5arXiv · cs.LG·16d ago·source ↗

Tight Convergence Theory for Error Feedback Algorithms in Distributed Optimization

This paper provides tight convergence analyses for two major error-feedback algorithms—classic Error Feedback (EF) and Error Feedback 21 (EF21)—used to mitigate communication bottlenecks in distributed learning. The authors identify optimal step-size choices and construct tailored Lyapunov functions for each method, yielding guarantees that hold independently of the number of agents and recover the best known single-agent bounds. The work clarifies the relative performance of these gradient compression variants, which has remained poorly understood despite widespread use.