AISTATS 2017poster82 citations

Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection

Lijie Chen, Jian Li, Mingda Qiao

Abstract

In the Best-k-Arm problem, we are given n stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the k arms with the largest means by taking as few samples as possible. In this paper, we make progress towards a complete characterization of the instance-wise sample complexity bounds for the Best-k-Arm problem. On the lower bound side, we obtain a novel complexity term to measure the sample complexity that every Best-k-Arm instance requires. This is derived by an interesting and nontrivial reduction from the Best-1-Arm problem. We also provide an elimination-based algorithm that matches the instance-wise lower bound within doubly-logarithmic factors. The sample complexity of our algorithm strictly dominates the state-of-the-art for Best-k-Arm (module constant factors).

BibTeX
@InProceedings{pmlr-v54-chen17a,
  title = 	 {{Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection}},
  author = 	 {Chen, Lijie and Li, Jian and Qiao, Mingda},
  booktitle = 	 {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {101--110},
  year = 	 {2017},
  editor = 	 {Singh, Aarti and Zhu, Jerry},
  volume = 	 {54},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {20--22 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v54/chen17a/chen17a.pdf},
  url = 	 {https://proceedings.mlr.press/v54/chen17a.html},
  abstract = 	 {In the Best-k-Arm problem, we are given n stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the k arms with the largest means by taking as few samples as possible. In this paper, we make progress towards a complete characterization of the instance-wise sample complexity bounds for the Best-k-Arm problem. On the lower bound side, we obtain a novel complexity term to measure the sample complexity that every Best-k-Arm instance requires. This is derived by an interesting and nontrivial reduction from the Best-1-Arm problem. We also provide an elimination-based algorithm that matches the instance-wise lower bound within doubly-logarithmic factors. The sample complexity of our algorithm strictly dominates the state-of-the-art for Best-k-Arm (module constant factors).}
}
Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection · AISTATS 2017