A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification
Paper i proceeding, 2024

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.

Contextual bandits

Combinatorial bandits

Online learning

Bottleneck identification

Författare

Fazeleh Sadat Hoseini

Nätverk och System

Niklas Åkerblom

Volvo Cars

Morteza Haghir Chehreghani

Chalmers, Data- och informationsteknik, Data Science och AI

International Conference on Information and Knowledge Management, Proceedings

21550751 (ISSN)

3782-3786

33rd ACM International Conference on Information and Knowledge Management, CIKM 2024
Boise, USA,

EENE: Energieffektiv Navigering för Elfordon

FFI - Fordonsstrategisk forskning och innovation (2018-01937), 2019-01-01 -- 2022-12-31.

Ämneskategorier

Datavetenskap (datalogi)

DOI

10.48550/arXiv.2206.08144

Mer information

Senast uppdaterat

2024-12-11