Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks
- 7 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (9), 1939-1943
- https://doi.org/10.1109/lwc.2021.3087156
Abstract
We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of ${O}$ (1/( nT )) in which ${n}$ is the number of devices and ${T}$ is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset.Keywords
Funding Information
- JST CREST (JPMJCR19F6)
This publication has 13 references indexed in Scilit:
- Distributed SGD With Flexible Gradient CompressionIEEE Access, 2020
- Toward an Intelligent Edge: Wireless Communication Meets Machine LearningIEEE Communications Magazine, 2020
- Stochastic Dual Averaging for Decentralized Online Optimization on Time-Varying Communication GraphsIEEE Transactions on Automatic Control, 2017
- Asynchronous distributed optimization using a randomized alternating direction method of multipliersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Distributed Alternating Direction Method of MultipliersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network ScalingIEEE Transactions on Automatic Control, 2011
- Distributed Compressive Spectrum Sensing in Cooperative Multihop Cognitive NetworksIEEE Journal of Selected Topics in Signal Processing, 2010
- Decentralized Sparse Signal Recovery for Compressive Sleeping Wireless Sensor NetworksIEEE Transactions on Signal Processing, 2010
- A Randomized Incremental Subgradient Method for Distributed Optimization in Networked SystemsSIAM Journal on Optimization, 2010
- Consensus in Ad Hoc WSNs With Noisy Links—Part I: Distributed Estimation of Deterministic SignalsIEEE Transactions on Signal Processing, 2007