Optimal convergence rates of totally asynchronous optimization
From MaRDI portal
Abstract: Asynchronous optimization algorithms are at the core of modern machine learning and resource allocation systems. However, most convergence results consider bounded information delays and several important algorithms lack guarantees when they operate under total asynchrony. In this paper, we derive explicit convergence rates for the proximal incremental aggregated gradient (PIAG) and the asynchronous block-coordinate descent (Async-BCD) methods under a specific model of total asynchrony, and show that the derived rates are order-optimal. The convergence bounds provide an insightful understanding of how the growth rate of the delays deteriorates the convergence times of the algorithms. Our theoretical findings are demonstrated by a numerical example.
This page was built for publication: Optimal convergence rates of totally asynchronous optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6393212)
