On the Necessity of Collaboration in Online Model Selection with Decentralized Data

arXiv:2404.09494v1 Announce Type: new
Abstract: We consider online model selection with decentralized data over $M$ clients, and study a fundamental problem: the necessity of collaboration. Previous work gave a negative answer from the perspective of worst-case regret minimization, while we give a different answer from the perspective of regret-computational cost trade-off. We separately propose a federated algorithm with and without communication constraint and prove regret bounds that show (i) collaboration is unnecessary if we do not limit the computational cost …

abstract arxiv case collaboration cs.lg data decentralized decentralized data model selection negative perspective study type work