Online Learning of Network Bottlenecks via Minimax Paths
Abstract
In this paper, we study bottleneck identification in networks via extracting minimax paths. Many real-world networks have stochastic weights for which full knowledge is not available in advance. Therefore, we model this task as a combinatorial semi-bandit problem to which we apply a combinatorial version of Thompson Sampling and establish an upper bound on the corresponding Bayesian regret. Due to the computational intractability of the problem, we then devise an alternative problem formulation which approximates the original objective. Finally, we experimentally evaluate the performance of Thompson Sampling with the approximate formulation on real-world directed and undirected networks.
Cite
Text
Åkerblom et al. "Online Learning of Network Bottlenecks via Minimax Paths." Machine Learning, 2023. doi:10.1007/S10994-022-06270-0Markdown
[Åkerblom et al. "Online Learning of Network Bottlenecks via Minimax Paths." Machine Learning, 2023.](https://mlanthology.org/mlj/2023/akerblom2023mlj-online/) doi:10.1007/S10994-022-06270-0BibTeX
@article{akerblom2023mlj-online,
title = {{Online Learning of Network Bottlenecks via Minimax Paths}},
author = {Åkerblom, Niklas and Hoseini, Fazeleh Sadat and Chehreghani, Morteza Haghir},
journal = {Machine Learning},
year = {2023},
pages = {131-150},
doi = {10.1007/S10994-022-06270-0},
volume = {112},
url = {https://mlanthology.org/mlj/2023/akerblom2023mlj-online/}
}