Top Arm Identification in Multi-Armed Bandits with Batch Arm Pulls

@inproceedings{Jun2016TopAI,
  title={Top Arm Identification in Multi-Armed Bandits with Batch Arm Pulls},
  author={Kwang-Sung Jun and Kevin G. Jamieson and Robert D. Nowak and Xiaojin Zhu},
  booktitle={AISTATS},
  year={2016}
}
We introduce a new multi-armed bandit (MAB) problem in which arms must be sampled in batches, rather than one at a time. This is motivated by applications in social media monitoring and biological experimentation where such batch constraints naturally arise. This paper develops and analyzes algorithms for batch MABs and top arm identification, for both fixed confidence and fixed budget settings. Our main theoretical results show that the batch constraint does not significantly a↵ect the sample… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 12 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 24 references

On the Complexity of Best Arm Identification in Multi-Armed Bandit Models

Journal of Machine Learning Research • 2016
View 4 Excerpts
Highly Influenced

Szepesvri, “On identifying good options under combinatorially structured feedback in finite noisy environments.

Y. Wu, A. Gyrgy
Proceedings of the International Conference on Machine Learning (ICML), • 2015
View 1 Excerpt

Best-arm identification algorithms for multi-armed bandits in the fixed confidence setting

2014 48th Annual Conference on Information Sciences and Systems (CISS) • 2014
View 1 Excerpt

Similar Papers

Loading similar papers…