AI RESEARCH
Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications
arXiv CS.LG
•
ArXi:2604.09276v1 Announce Type: new Distributed online convex optimization (D-OCO) is a powerful paradigm for modeling distributed scenarios with streaming data. However, the communication cost between local learners and the central server is substantial in large-scale applications. To alleviate this bottleneck, we initiate the study of D-OCO with compressed communication.