Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhuang, Yi, Yang, Kun, Chen, Xingran
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914260004634624
author Zhuang, Yi
Yang, Kun
Chen, Xingran
author_facet Zhuang, Yi
Yang, Kun
Chen, Xingran
contents We study a decentralized collaborative requesting problem that aims to optimize the information freshness of time-sensitive clients in edge networks consisting of multiple clients, access nodes (ANs), and servers. Clients request content through ANs acting as gateways, without observing AN states or the actions of other clients. We define the reward as the age of information reduction resulting from a client's selection of an AN, and formulate the problem as a non-stationary multi-armed bandit. In this decentralized and partially observable setting, the resulting reward process is history-dependent and coupled across clients, and exhibits both abrupt and gradual changes in expected rewards, rendering classical bandit-based approaches ineffective. To address these challenges, we propose the AGING BANDIT WITH ADAPTIVE RESET algorithm, which combines adaptive windowing with periodic monitoring to track evolving reward distributions. We establish theoretical performance guarantees showing that the proposed algorithm achieves near-optimal performance, and we validate the theoretical results through simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08760
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits
Zhuang, Yi
Yang, Kun
Chen, Xingran
Machine Learning
Multiagent Systems
We study a decentralized collaborative requesting problem that aims to optimize the information freshness of time-sensitive clients in edge networks consisting of multiple clients, access nodes (ANs), and servers. Clients request content through ANs acting as gateways, without observing AN states or the actions of other clients. We define the reward as the age of information reduction resulting from a client's selection of an AN, and formulate the problem as a non-stationary multi-armed bandit. In this decentralized and partially observable setting, the resulting reward process is history-dependent and coupled across clients, and exhibits both abrupt and gradual changes in expected rewards, rendering classical bandit-based approaches ineffective. To address these challenges, we propose the AGING BANDIT WITH ADAPTIVE RESET algorithm, which combines adaptive windowing with periodic monitoring to track evolving reward distributions. We establish theoretical performance guarantees showing that the proposed algorithm achieves near-optimal performance, and we validate the theoretical results through simulations.
title Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2601.08760