BEER: Fast O(1/T) rate for decentralized nonconvex optimization with communication compression

Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments. To tackle the communication bottleneck, there have been many efforts to design communication-compressed algorithms for decentral...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHAO, Haoyu, LI, Boyue, LI, Zhize, RICHTARIK, Peter, CHI, Yuejie
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8687
https://ink.library.smu.edu.sg/context/sis_research/article/9690/viewcontent/NeurIPS22_full_beer.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Be the first to leave a comment!
You must be logged in first