The Impact of Batch Learning in Stochastic Linear Bandits.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Samenvatting

We consider a special case of bandit problems, named batched bandits, in which an agent observes batches of responses over a certain time period. Unlike previous work, we consider a more practically relevant batch-centric scenario of batch learning. That is to say, we provide a policy-agnostic regret analysis and demonstrate upper and lower bounds for the regret of a candidate policy. Our main theoretical results show that the impact of batch learning is a multiplicative factor of batch size relative to the regret of online behavior. Primarily, we study two settings of the stochastic linear bandits: bandits with finitely and infinitely many arms. While the regret bounds are the same for both settings, the former setting results hold under milder assumptions. Also, we provide a more robust result for the 2-armed bandit problem as an important insight. Finally, we demonstrate the consistency of theoretical results by conducting empirical experiments and reflect on optimal batch size choice.

Originele taal-2Engels
TitelProceedings - 22nd IEEE International Conference on Data Mining, ICDM 2022
RedacteurenXingquan Zhu, Sanjay Ranka, My T. Thai, Takashi Washio, Xindong Wu
Pagina's1149-1154
Aantal pagina's6
ISBN van elektronische versie9781665450997
DOI's
StatusGepubliceerd - 2022

Bibliografische nota

DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

Vingerafdruk

Duik in de onderzoeksthema's van 'The Impact of Batch Learning in Stochastic Linear Bandits.'. Samen vormen ze een unieke vingerafdruk.

Citeer dit