Delay-agnostic Asynchronous Coordinate Update Algorithm
From MaRDI portal
Publication:6436615
arXiv2305.08535MaRDI QIDQ6436615FDOQ6436615
Xuyang Wu, Sindri Magnússon, Changxin Liu, Mikael Johansson
Publication date: 15 May 2023
Abstract: We propose a delay-agnostic asynchronous coordinate update algorithm (DEGAS) for computing operator fixed points, with applications to asynchronous optimization. DEGAS includes novel asynchronous variants of ADMM and block-coordinate descent as special cases. We prove that DEGAS converges under both bounded and unbounded delays under delay-free parameter conditions. We also validate by theory and experiments that DEGAS adapts well to the actual delays. The effectiveness of DEGAS is demonstrated by numerical experiments on classification problems.
This page was built for publication: Delay-agnostic Asynchronous Coordinate Update Algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6436615)
