# Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits

arXiv: https://arxiv.org/abs/2601.08760 · HTML: https://mlsanity.com/paper/2601.08760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 18 of 18)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Age of Information: An Introduction and Survey](https://mlsanity.com/paper/2007.08564/) (2020)
- [Age of Information: Whittle Index for Scheduling Stochastic Arrivals](https://mlsanity.com/paper/1801.03422/) (2018)
- [A Whittle Index Approach to Minimizing Functions of Age of Information](https://mlsanity.com/paper/1908.10438/) (2019)
- [Sliding-Window Thompson Sampling for Non-Stationary Settings](https://mlsanity.com/paper/2409.05181/) (2024)
- [AoI Minimization in Status Update Control with Energy Harvesting Sensors](https://mlsanity.com/paper/2009.04224/) (2020)
- [Collaborative Multi-Agent Multi-Armed Bandit Learning for Small-Cell Caching](https://mlsanity.com/paper/2001.03835/) (2020)
- [Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits](https://mlsanity.com/paper/2107.11419/) (2021)
- [When Decentralized Optimization Meets Federated Learning](https://mlsanity.com/paper/2306.02570/) (2023)
- [Age of Information in Random Access Channels](https://mlsanity.com/paper/1912.01473/) (2019)
- [Real-time Sampling and Estimation on Random Access Channels: Age of Information and Beyond](https://mlsanity.com/paper/2007.03652/) (2020)
- [Can Decentralized Status Update Achieve Universally Near-Optimal Age-of-Information in Wireless Multiaccess Channels?](https://mlsanity.com/paper/1803.08189/) (2018)
- [Information Freshness in Cache Updating Systems](https://mlsanity.com/paper/2004.09475/) (2020)
- [On the Global Optimality of Whittle's index policy for minimizing the age of information](https://mlsanity.com/paper/2102.02528/) (2021)
- [Optimizing AoI at Query in Multiuser Wireless Uplink Networks: A Whittle Index Approach](https://mlsanity.com/paper/2411.02108/) (2024)
- [Optimal Content Caching and Recommendation with Age of Information](https://mlsanity.com/paper/2111.11608/) (2021)
- [Containing a spread through sequential learning: to exploit or to explore?](https://mlsanity.com/paper/2303.00141/) (2023)
- [Timely Requesting for Time-Critical Content Users in Decentralized F-RANs](https://mlsanity.com/paper/2407.02930/) (2024)

## Abstract (arXiv)

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.