A multi-armed bandit-based approach to mobile network provider selection

T Sandholm, S Mukherjee - arXiv preprint arXiv:2012.04755, 2020 - arxiv.org
We argue for giving users the ability to lease bandwidth temporarily from any mobile network
operator. We propose, prototype, and evaluate a spectrum market for mobile network …

Online Resource Allocation: Bandits feedback and Advice on Time-varying Demands

L Lyu, WC Cheung - arXiv preprint arXiv:2302.04182, 2023 - arxiv.org
We consider a general online resource allocation model with bandit feedback and time-
varying demands. While online resource allocation has been well studied in the literature …

Constrained Bandit Learning with Switching Costs for Wireless Networks

J Steiger, B Li, B Ji, N Lu - IEEE INFOCOM 2023-IEEE …, 2023 - ieeexplore.ieee.org
Bandits with arm selection constraints and bandits with switching costs have both gained
recent attention in wireless networking research. Pessimistic-optimistic algorithms, which …

Offline contextual bandits for wireless network optimization

M Suau, A Agapitos, D Lynch, D Farrell, M Zhou… - arXiv preprint arXiv …, 2021 - arxiv.org
The explosion in mobile data traffic together with the ever-increasing expectations for higher
quality of service call for the development of AI algorithms for wireless network optimization …

Wireless optimisation via convex bandits: unlicensed LTE/WiFi coexistence

C Cano, G Neu - Proceedings of the 2018 Workshop on Network Meets …, 2018 - dl.acm.org
Bandit Convex Optimisation (BCO) is a powerful framework for sequential decision-making
in non-stationary and partially observable environments. In a BCO problem, a decision …

Constrained thompson sampling for wireless link optimization

V Saxena, JE Gonzalez, I Stoica, H Tullberg… - arXiv preprint arXiv …, 2019 - arxiv.org
Wireless communication systems operate in complex time-varying environments. Therefore,
selecting the optimal configuration parameters in these systems is a challenging problem …

Combinatorial bandits for incentivizing agents with dynamic preferences

T Fiez, S Sekar, L Zheng, LJ Ratliff - arXiv preprint arXiv:1807.02297, 2018 - arxiv.org
The design of personalized incentives or recommendations to improve user engagement is
gaining prominence as digital platform providers continually emerge. We propose a multi …

A Contextual Bandit Approach for Network Service Selection

Z Li, R Zhang, S Zhou, H Yu… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
As large companies expand their operations, the importance of the business-to-business
(B2B) model is also on the rise. The network service selection problem serves as a typical …

[HTML][HTML] Bandit Methods for Network Optimization: Safety, Exploration, and Coordination

F Vannella - 2023 - diva-portal.org
The increasing complexity of modern mobile networks poses unprecedented challenges to
their optimization. Mobile Network Operators (MNOs) need to control a large number of …

Communication-Efficient Cooperative Contextual Bandit and Its Application to Wi-Fi BSS Selection

T Sakakibara, T Nishio, A Taya… - 2020 IEEE 17th …, 2020 - ieeexplore.ieee.org
In this study, we extended a contextual bandit algorithm, LinUCB, to facilitate cooperative
learning of an optimal strategy with intermittent information sharing. We then applied the …