AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression

arXiv:2404.05919v1 Announce Type: new
Abstract: Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server. However, the communication overhead remains a major bottleneck for the practical realization of such decentralized setups. To tackle this issue, several algorithms for decentralized training with compressed communication have been proposed in the literature. Most of these algorithms introduce an additional hyper-parameter referred to as consensus step-size which is tuned based on the compression ratio at …

abstract algorithms arxiv communication compression consensus cs.lg datasets decentralized deep learning distributed however issue major on-device learning practical server training type