Random gradient extrapolation for distributed and stochastic optimization

TL;DR

This paper introduces RGEM, a novel randomized gradient method for distributed convex optimization that achieves optimal complexity bounds in gradient evaluations and communication rounds, without requiring exact initial gradients.

Contribution

The paper develops RGEM, a new randomized incremental gradient algorithm that attains optimal complexity bounds for distributed and stochastic convex optimization without initial gradient evaluations.

Findings

Achieves ${ m O}(\log(1/\epsilon))$ gradient complexity.

Maintains ${ m O}(1/\epsilon)$ stochastic gradient complexity.

Requires only one agent per communication round.

Abstract

In this paper, we consider a class of finite-sum convex optimization problems defined over a distributed multiagent network with $m$ agents connected to a central server. In particular, the objective function consists of the average of $m$ ($\ge 1$) smooth components associated with each network agent together with a strongly convex term. Our major contribution is to develop a new randomized incremental gradient algorithm, namely random gradient extrapolation method (RGEM), which does not require any exact gradient evaluation even for the initial point, but can achieve the optimal ${\cal O}(\log(1/\epsilon))$ complexity bound in terms of the total number of gradient evaluations of component functions to solve the finite-sum problems. Furthermore, we demonstrate that for stochastic finite-sum optimization problems, RGEM maintains the optimal ${\cal O}(1/\epsilon)$ complexity (up to a certain logarithmic factor) in terms of the number of stochastic gradient computations, but attains an ${\cal O}(\log(1/\epsilon))$ complexity in terms of communication rounds (each round involves only one agent). It is worth noting that the former bound is independent of the number of agents $m$, while the latter one only linearly depends on $m$ or even $\sqrt m$ for ill-conditioned problems. To the best of our knowledge, this is the first time that these complexity bounds have been obtained for distributed and stochastic optimization problems. Moreover, our algorithms were developed based on a novel dual perspective of Nesterov's accelerated gradient method.