Communication-Censored Linearized ADMM for Decentralized Consensus Optimization

TL;DR

This paper introduces COLA, a communication- and computation-efficient decentralized optimization algorithm that combines linearization and censoring strategies to reduce costs while ensuring convergence.

Contribution

The paper proposes COLA, a novel algorithm that integrates linearization and communication-censoring to improve efficiency in decentralized consensus optimization.

Findings

COLA converges under Lipschitz continuous gradients.

Linear (sublinear) decay of censoring threshold yields linear (sublinear) convergence.

Numerical results confirm the efficiency and effectiveness of COLA.

Abstract

In this paper, we propose a communication- and computation-efficient algorithm to solve a convex consensus optimization problem defined over a decentralized network. A remarkable existing algorithm to solve this problem is the alternating direction method of multipliers (ADMM), in which at every iteration every node updates its local variable through combining neighboring variables and solving an optimization subproblem. The proposed algorithm, called as COmmunication-censored Linearized ADMM (COLA), leverages a linearization technique to reduce the iteration-wise computation cost of ADMM and uses a communication-censoring strategy to alleviate the communication cost. To be specific, COLA introduces successive linearization approximations to the local cost functions such that the resultant computation is first-order and light-weight. Since the linearization technique slows down the convergence speed, COLA further adopts the communication-censoring strategy to avoid transmissions of less informative messages. A node is allowed to transmit only if the distance between the current local variable and its previously transmitted one is larger than a censoring threshold. COLA is proven to be convergent when the local cost functions have Lipschitz continuous gradients and the censoring threshold is summable. When the local cost functions are further strongly convex, we establish the linear (sublinear) convergence rate of COLA, given that the censoring threshold linearly (sublinearly) decays to 0. Numerical experiments corroborate with the theoretical findings and demonstrate the satisfactory communication-computation tradeoff of COLA.