Optimal combination policies for adaptive social learning
File(s)
Accepted version
Author(s)
Hu, Ping
Bordignon, Virginia
Vlaski, Stefan
Saye, Ali H
Type
Conference Paper
Abstract
This paper investigates the effect of combination policies on the performance of adaptive social learning in non-stationary environments. By analyzing the relation between the error probability and the underlying graph topology, we prove that in the slow adaptation regime, combination policies with a uniform Perron eigenvector will provide the smallest steady-state error probability. This result indicates that in terms of learning accuracy, doubly-stochastic combination policies yield optimal performance. Moreover, we estimate the adaptation time of adaptive social learning in the small signal-to-noise regime and show that in this regime, the influence of combination policies on the adaptation time is insignificant.
Date Issued
2022-04-27
Date Acceptance
2022-04-01
Citation
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp.5842-5846
ISSN
1520-6149
Publisher
IEEE
Start Page
5842
End Page
5846
Journal / Book Title
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Copyright Statement
Copyright © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000864187906028&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
Source
47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Subjects
Acoustics
adaptation time
combination policy
Computer Science
Computer Science, Artificial Intelligence
Engineering
Engineering, Electrical & Electronic
large deviations
NETWORKS
Science & Technology
Social learning
Technology
Publication Status
Published
Start Date
2022-05-22
Finish Date
2022-05-27
Coverage Spatial
SINGAPORE, Singapore