A Sequential Gradient-Based Multiple Access for Distributed Learning over Fading Channels

Tomer Sery, Kobi Cohen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

A distributed learning problem over multiple access channel (MAC) using a large wireless network is considered. The objective function is a sum of the nodes' local loss functions. The inference decision is made by the network edge and is based on received data from distributed nodes which transmit over a noisy fading MAC. We develop a novel Gradient-Based Multiple Access (GBMA) algorithm to solve the distributed learning problem over MAC. Specifically, the nodes transmit an analog function of the local gradient using common shaping waveforms. The network edge receives a superposition of the analog transmitted signals which represents a noisy distorted gradient used for updating the estimate. We analyze the performance of GBMA theoretically, and prove that it can approach the convergence rate of the centralized gradient descent (GD) algorithm in large networks under both convex and strongly convex loss functions with Lipschitz gradient.

Original languageEnglish
Title of host publication2019 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages303-307
Number of pages5
ISBN (Electronic)9781728131511
DOIs
StatePublished - 1 Sep 2019
Event57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019 - Monticello, United States
Duration: 24 Sep 201927 Sep 2019

Publication series

Name2019 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019

Conference

Conference57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019
Country/TerritoryUnited States
CityMonticello
Period24/09/1927/09/19

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality
  • Control and Optimization

Fingerprint

Dive into the research topics of 'A Sequential Gradient-Based Multiple Access for Distributed Learning over Fading Channels'. Together they form a unique fingerprint.

Cite this