English

A Batch Sequential Halving Algorithm without Performance Degradation

Machine Learning 2024-06-04 v1 Machine Learning

Abstract

In this paper, we investigate the problem of pure exploration in the context of multi-armed bandits, with a specific focus on scenarios where arms are pulled in fixed-size batches. Batching has been shown to enhance computational efficiency, but it can potentially lead to a degradation compared to the original sequential algorithm's performance due to delayed feedback and reduced adaptability. We introduce a simple batch version of the Sequential Halving (SH) algorithm (Karnin et al., 2013) and provide theoretical evidence that batching does not degrade the performance of the original algorithm under practical conditions. Furthermore, we empirically validate our claim through experiments, demonstrating the robust nature of the SH algorithm in fixed-size batch settings.

Keywords

Cite

@article{arxiv.2406.00424,
  title  = {A Batch Sequential Halving Algorithm without Performance Degradation},
  author = {Sotetsu Koyamada and Soichiro Nishimori and Shin Ishii},
  journal= {arXiv preprint arXiv:2406.00424},
  year   = {2024}
}

Comments

Accepted to RLC 2024

R2 v1 2026-06-28T16:49:34.447Z