IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2201.04469.html
   My bibliography  Save this paper

Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap

Author

Listed:
  • Masahiro Kato
  • Kaito Ariu
  • Masaaki Imaizumi
  • Masahiro Nomura
  • Chao Qin

Abstract

We consider fixed-budget best-arm identification in two-armed Gaussian bandit problems. One of the longstanding open questions is the existence of an optimal strategy under which the probability of misidentification matches a lower bound. We show that a strategy following the Neyman allocation rule (Neyman, 1934) is asymptotically optimal when the gap between the expected rewards is small. First, we review a lower bound derived by Kaufmann et al. (2016). Then, we propose the "Neyman Allocation (NA)-Augmented Inverse Probability weighting (AIPW)" strategy, which consists of the sampling rule using the Neyman allocation with an estimated standard deviation and the recommendation rule using an AIPW estimator. Our proposed strategy is optimal because the upper bound matches the lower bound when the budget goes to infinity and the gap goes to zero.

Suggested Citation

  • Masahiro Kato & Kaito Ariu & Masaaki Imaizumi & Masahiro Nomura & Chao Qin, 2022. "Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap," Papers 2201.04469, arXiv.org, revised Dec 2022.
  • Handle: RePEc:arx:papers:2201.04469
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2201.04469
    File Function: Latest version
    Download Restriction: no
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Masahiro Kato & Masaaki Imaizumi & Takuya Ishihara & Toru Kitagawa, 2022. "Best Arm Identification with Contextual Information under a Small Gap," Papers 2209.07330, arXiv.org, revised Jan 2023.
    2. Karun Adusumilli, 2022. "Neyman allocation is minimax optimal for best arm identification with two arms," Papers 2204.05527, arXiv.org, revised Aug 2022.
    3. Jinglong Zhao, 2023. "Adaptive Neyman Allocation," Papers 2309.08808, arXiv.org, revised Sep 2023.
    4. Jinglong Zhao, 2024. "Experimental Design For Causal Inference Through An Optimization Lens," Papers 2408.09607, arXiv.org, revised Aug 2024.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2201.04469. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.