Volume 35, Issue 4
Extrapush for Convex Smooth Decentralized Optimization Over Directed Networks

Jinshan Zeng and Wotao Yin

10.4208/jcm.1606-m2015-0452

J. Comp. Math., 35 (2017), pp. 383-396.

Preview Full PDF BiBTex 1 426
  • Abstract

In this note, we extend the algorithms Extra [13] and subgradient-push [10] 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.

  • History

Published online: 2017-08

  • AMS Subject Headings

90C25, 90C30.

  • Cited by