Scalable Decentralized Algorithms for Online Personalized Mean Estimation

arXiv:2402.12812v1 Announce Type: new
Abstract: In numerous settings, agents lack sufficient data to directly learn a model. Collaborating with other agents may help, but it introduces a bias-variance trade-off, when local data distributions differ. A key challenge is for each agent to identify clients with similar distributions while learning the model, a problem that remains largely unresolved. This study focuses on a simplified version of the overarching problem, where each agent collects samples from a real-valued distribution over time to …

abstract agent agents algorithms arxiv bias bias-variance challenge cs.dc cs.lg data decentralized identify key learn mean personalized scalable trade trade-off type variance