Faster rates for compressed federated learning with client-variance reduction

• Main Authors: ZHAO, Haoyu, BURLACHENKO, Konstantin, LI, Zhize, RICHTARIK, Peter
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: federated learning; distributed optimization; communication compression; variance reduction; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9607; https://ink.library.smu.edu.sg/context/sis_research/article/10607/viewcontent/SIMODS24_cofig_av.pdf
• Institution: Singapore Management University

Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity, and limited availability of clients result in high c...