ExtraPush for convex smooth decentralized optimization over directed networks

TL;DR

This paper introduces ExtraPush and Normalized ExtraPush algorithms for convex smooth decentralized optimization over directed networks, allowing fixed step sizes and column-stochastic mixing matrices, and demonstrating faster convergence than subgradient-push.

Contribution

The paper extends existing algorithms to directed networks with fixed step sizes and column-stochastic matrices, removing the undirected network restriction and providing convergence analysis.

Findings

ExtraPush and Normalized ExtraPush outperform subgradient-push in speed.

Normalized ExtraPush converges linearly for strongly convex objectives.

Both algorithms work with fixed step sizes and column-stochastic matrices.

Abstract

In this note, we extend the algorithms Extra and subgradient-push to a new algorithm ExtraPush for consensus optimization with convex differentiable objective functions over a directed network. When the stationary distribution of the network can be computed in advance}, we propose a simplified algorithm called Normalized ExtraPush. Just like Extra, both ExtraPush and Normalized ExtraPush can iterate with a fixed step size. But unlike Extra, they can take a column-stochastic mixing matrix, which is not necessarily doubly stochastic. Therefore, they remove the undirected-network restriction of Extra. Subgradient-push, while also works for directed networks, is slower on the same type of problem because it must use a sequence of diminishing step sizes. We present preliminary analysis for ExtraPush under a bounded sequence assumption. For Normalized ExtraPush, we show that it naturally produces a bounded, linearly convergent sequence provided that the objective function is strongly convex. In our numerical experiments, ExtraPush and Normalized ExtraPush performed similarly well. They are significantly faster than subgradient-push, even when we hand-optimize the step sizes for the latter.