Decentralized Optimization over Noisy, Rate-Constrained Networks: Achieving Consensus by Communicating Differences

Rajarshi Saha, Stefano Rini, Milind Rao, Andrea J. Goldsmith

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In decentralized optimization, multiple nodes in a network collaborate to minimize the sum of their local loss functions. The information exchange between nodes required for this task, is often limited by network connectivity. We consider a setting in which communication between nodes is hindered by both (i) a finite rate-constraint on the signal transmitted by any node, and (ii) additive noise corrupting the signal received by any node. We propose a novel algorithm for this scenario: Decentralized Lazy Mirror Descent with Differential Exchanges (DLMD-DiffEx), which guarantees convergence of the local estimates to the optimal solution under the given communication constraints. A salient feature of DLMD-DiffEx is the introduction of additional proxy variables that are maintained by the nodes to account for the disagreement in their estimates due to channel noise and rate-constraints. Convergence to the optimal solution is attained by having nodes iteratively exchange these disagreement terms until consensus is achieved. In order to prevent noise accumulation during this exchange, DLMD-DiffEx relies on two sequences: one controlling the power of the transmitted signal, and the other determining the consensus rate. We provide insights on the design of these two sequences which highlights the interplay between consensus rate and noise amplification. We investigate the performance of DLMD-DiffEx both from a theoretical perspective as well as through numerical evaluations on synthetic data and MNIST. MATLAB and Python implementations can be found at https://github.com/rajarshisaha95/DLMD-DiffEx.

Original languageEnglish (US)
Pages (from-to)449-467
Number of pages19
JournalIEEE Journal on Selected Areas in Communications
Volume40
Issue number2
DOIs
StatePublished - Feb 1 2022

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Keywords

  • Decentralized optimization
  • additive channel noise
  • finite data rate constraint
  • lazy mirror descent

Fingerprint

Dive into the research topics of 'Decentralized Optimization over Noisy, Rate-Constrained Networks: Achieving Consensus by Communicating Differences'. Together they form a unique fingerprint.

Cite this