Skip to main content

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

Author(s): Saha, Rajarshi; Rini, Stefano; Rao, Milind; Goldsmith, Andrea J

To refer to this page use:
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
Publication Date: 6-Oct-2021
Citation: Saha, Rajarshi, Rini, Stefano, Rao, Milind, Goldsmith, Andrea J. (2022). Decentralized Optimization Over Noisy, Rate-Constrained Networks: Achieving Consensus by Communicating Differences. IEEE Journal on Selected Areas in Communications, 40 (2), 449 - 467. doi:10.1109/jsac.2021.3118428
DOI: doi:10.1109/jsac.2021.3118428
ISSN: 0733-8716
EISSN: 1558-0008
Pages: 449 - 467
Type of Material: Journal Article
Journal/Proceeding Title: IEEE Journal on Selected Areas in Communications
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.