# Learning to Schedule in Non-Stationary Wireless Networks With Unknown Statistics

arXiv: https://arxiv.org/abs/2308.02734 · HTML: https://mlsanity.com/paper/2308.02734/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 4 Aug 2023.

## Builds on (most cited first, 5 of 5)

- [Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications](https://mlsanity.com/paper/1703.01610/) (2017)
- [Tracking the Best Expert in Non-stationary Stochastic Environments](https://mlsanity.com/paper/1712.00578/) (2017)
- [Combinatorial Semi-Bandit in the Non-Stationary Environment](https://mlsanity.com/paper/2002.03580/) (2020)
- [Joint Scheduling of URLLC and eMBB Traffic in 5G Wireless Networks](https://mlsanity.com/paper/1712.05344/) (2017)
- [An Online Algorithm for Computation Offloading in Non-Stationary Environments](https://mlsanity.com/paper/2006.12032/) (2020)

## Built on by (most cited first, 1 of 1)

- [MAB-Based Channel Scheduling for Asynchronous Federated Learning in Non-Stationary Environments](https://mlsanity.com/paper/2503.01324/) (2025)

## Abstract (arXiv)

The emergence of large-scale wireless networks with partially-observable and time-varying dynamics has imposed new challenges on the design of optimal control policies. This paper studies efficient scheduling algorithms for wireless networks subject to generalized interference constraint, where mean arrival and mean service rates are unknown and non-stationary. This model exemplifies realistic edge devices' characteristics of wireless communication in modern networks. We propose a novel algorithm termed MW-UCB for generalized wireless network scheduling, which is based on the Max-Weight policy and leverages the Sliding-Window Upper-Confidence Bound to learn the channels' statistics under non-stationarity. MW-UCB is provably throughput-optimal under mild assumptions on the variability of mean service rates. Specifically, as long as the total variation in mean service rates over any time period grows sub-linearly in time, we show that MW-UCB can achieve the stability region arbitrarily close to the stability region of the class of policies with full knowledge of the channel statistics. Extensive simulations validate our theoretical results and demonstrate the favorable performance of MW-UCB.