Generalization Error Matters in Decentralized Learning Under Byzantine Attacks
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Signal Processing"
DOI: 10.1109/tsp.2025.3526989
Abstract: Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central server. When some… read more here.
Keywords: decentralized learning; generalization error; byzantine; error matters ... See more keywords