English

A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification

Machine Learning 2023-03-07 v2

Abstract

Bottleneck identification is a challenging task in network analysis, especially when the network is not fully specified. To address this task, we develop a unified online learning framework based on combinatorial semi-bandits that performs bottleneck identification in parallel with learning the specifications of the underlying network. Within this framework, we adapt and study various combinatorial semi-bandit methods such as epsilon-greedy, LinUCB, BayesUCB, NeuralUCB, and Thompson Sampling. In addition, our framework is capable of using contextual information in the form of contextual bandits. Finally, we evaluate our framework on the real-world application of road networks and demonstrate its effectiveness in different settings.

Keywords

Cite

@article{arxiv.2206.08144,
  title  = {A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification},
  author = {Fazeleh Hoseini and Niklas Åkerblom and Morteza Haghir Chehreghani},
  journal= {arXiv preprint arXiv:2206.08144},
  year   = {2023}
}
R2 v1 2026-06-24T11:53:47.927Z