An Accelerated Second-Order Method for Distributed Stochastic Optimization
From MaRDI portal
Abstract: We consider distributed stochastic optimization problems that are solved with master/workers computation architecture. Statistical arguments allow to exploit statistical similarity and approximate this problem by a finite-sum problem, for which we propose an inexact accelerated cubic-regularized Newton's method that achieves lower communication complexity bound for this setting and improves upon existing upper bound. We further exploit this algorithm to obtain convergence rate bounds for the original stochastic optimization problem and compare our bounds with the existing bounds in several regimes when the goal is to minimize the number of communication rounds and increase the parallelization by increasing the number of workers.
This page was built for publication: An Accelerated Second-Order Method for Distributed Stochastic Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6363818)
