A Single-Loop Algorithm for Decentralized Bilevel Optimization

arXiv:2311.08945v3 Announce Type: replace-cross
Abstract: Bilevel optimization has gained significant attention in recent years due to its broad applications in machine learning. This paper focuses on bilevel optimization in decentralized networks and proposes a novel single-loop algorithm for solving decentralized bilevel optimization with a strongly convex lower-level problem. Our approach is a fully single-loop method that approximates the hypergradient using only two matrix-vector multiplications per iteration. Importantly, our algorithm does not require any gradient heterogeneity assumption, distinguishing it from existing …

abstract algorithm applications arxiv attention cs.dc cs.lg decentralized loop machine machine learning math.oc networks novel optimization paper type