Delay-agnostic Asynchronous Coordinate Update Algorithm

2023/05/15 by Wu, Xuyang, Liu, Changxin, Magnusson, Sindri +1 · 1 citation
#FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2305.08535

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.

Cited by

• Scalable Asynchronous Federated Modeling for Spatial Data

Related

• On Unbounded Delays in Asynchronous Parallel Fixed-Point Algorithms
• Asynchronous Coordinate Descent under More Realistic Assumptions
• A2BCD: An Asynchronous Accelerated Block Coordinate Descent Algorithm With Optimal Complexity
• Faster Asynchronous Nonconvex Block Coordinate Descent with Locally Chosen Stepsizes
• Cyclic Coordinate Update Algorithms for Fixed-Point Problems: Analysis and Applications