Decentralized ADMM with Compressed and Event-Triggered Communication

TL;DR

This paper introduces CC-DQM, a communication-efficient decentralized optimization algorithm that combines compression and event-triggered communication to achieve linear convergence with reduced communication and computation costs.

Contribution

It proposes a novel decentralized second-order optimization method integrating compressed and event-triggered communication with theoretical convergence guarantees.

Findings

Achieves exact linear convergence despite compression errors.

Reduces communication load through event-triggered updates.

Validates effectiveness via numerical experiments.

Abstract

This paper focuses on the decentralized optimization problem, where agents in a network cooperate to minimize the sum of their local objective functions by information exchange and local computation. Based on the alternating direction method of multipliers (ADMM), we propose CC-DQM, a communication-efficient decentralized second-order optimization algorithm that combines compressed communication with event-triggered communication. Specifically, agents are allowed to transmit the compressed message only when the current primal variables have changed greatly compared to its last estimate. Moreover, to relieve the computation cost, the update of Hessian is scheduled by the trigger condition. To maintain exact linear convergence under compression, we compress the difference between the information to be transmitted and its estimate by a general contractive compressor. Theoretical analysis shows that CC-DQM can still achieve an exact linear convergence, despite the existence of compression error and intermittent communication, if the objective functions are strongly convex and smooth. Finally, we validate the performance of CC-DQM by numerical experiments.