Improved Algorithm on Online Clustering of Bandits

Shuai Li, Wei Chen, Shuai Li, Kwong-Sak Leung

IJCAI 2019 pp. 2923-2929

doi:10.24963/IJCAI.2019/405 /ijcai/2019/li2019ijcai-improved/

Abstract

We generalize the setting of online clustering of bandits by allowing non-uniform distribution over user frequencies. A more efficient algorithm is proposed with simple set structures to represent clusters. We prove a regret bound for the new algorithm which is free of the minimal frequency over users. The experiments on both synthetic and real datasets consistently show the advantage of the new algorithm over existing methods.

PDF IJCAI Semantic Scholar

Cite

Text

Li et al. "Improved Algorithm on Online Clustering of Bandits." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/405

Markdown

[Li et al. "Improved Algorithm on Online Clustering of Bandits." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/li2019ijcai-improved/) doi:10.24963/IJCAI.2019/405

BibTeX

@inproceedings{li2019ijcai-improved,
  title     = {{Improved Algorithm on Online Clustering of Bandits}},
  author    = {Li, Shuai and Chen, Wei and Li, Shuai and Leung, Kwong-Sak},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {2923-2929},
  doi       = {10.24963/IJCAI.2019/405},
  url       = {https://mlanthology.org/ijcai/2019/li2019ijcai-improved/}
}