A Communication Efficient Quasi-Newton Method for Large-scale Distributed Multi-agent Optimization

MaRDI QIDQ6387939zbMATH OpenFDO

Authors Yichuan Li, Petros G. Voulgaris, Nikolaos M. Freris

Publication date 10 January 2022

Abstract: We propose a communication efficient quasi-Newton method for large-scale multi-agent convex composite optimization. We assume the setting of a network of agents that cooperatively solve a global minimization problem with strongly convex local cost functions augmented with a non-smooth convex regularizer. By introducing consensus variables, we obtain a block-diagonal Hessian and thus eliminate the need for additional communication when approximating the objective curvature information. Moreover, we reduce computational costs of existing primal-dual quasi-Newton methods from $mathcalO(d^3)$ to $mathcalO(cd)$ by storing $c$ pairs of vectors of dimension $d$. An asynchronous implementation is presented that removes the need for coordination. Global linear convergence rate in expectation is established, and we demonstrate the merit of our algorithm numerically with real datasets.

This page was built for publication: A Communication Efficient Quasi-Newton Method for Large-scale Distributed Multi-agent Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6387939)