FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311014196> ?p ?o ?g. }

• W4311014196 endingPage "13" @default.
• W4311014196 startingPage "1" @default.
• W4311014196 abstract "This article studies an important sequential decision making problem known as the multi-armed stochastic bandit problem with covariates. Under a linear bandit framework with high-dimensional covariates, we propose a general multi-stage arm allocation algorithm that integrates both arm elimination and randomized assignment strategies. By employing a class of high-dimensional regression methods for coefficient estimation, the proposed algorithm is shown to have near optimal finite-time regret performance under a new study scope that requires neither a margin condition nor a reward gap condition for competitive arms. Based on the synergistically verified benefit of the margin, our algorithm exhibits adaptive performance that automatically adapts to the margin and gap conditions, and attains optimal regret rates simultaneously for both study scopes, without or with the margin, up to a logarithmic factor. Besides the desirable regret performance, the proposed algorithm simultaneously generates useful coefficient estimation output for competitive arms and is shown to achieve both estimation consistency and variable selection consistency. Promising empirical performance is demonstrated through extensive simulation and two real data evaluation examples. Supplementary materials for this article are available online." @default.
• W4311014196 created "2022-12-22" @default.
• W4311014196 creator A5035153981 @default.
• W4311014196 creator A5049225160 @default.
• W4311014196 creator A5079362198 @default.
• W4311014196 date "2023-01-11" @default.
• W4311014196 modified "2023-10-03" @default.
• W4311014196 title "Adaptive Algorithm for Multi-Armed Bandit Problem with High-Dimensional Covariates" @default.
• W4311014196 cites W1515782956 @default.
• W4311014196 cites W1570963478 @default.
• W4311014196 cites W1965125844 @default.
• W4311014196 cites W1973885534 @default.
• W4311014196 cites W1996437515 @default.
• W4311014196 cites W1996851858 @default.
• W4311014196 cites W1999245624 @default.
• W4311014196 cites W2009551863 @default.
• W4311014196 cites W2020925091 @default.
• W4311014196 cites W2043919728 @default.
• W4311014196 cites W2049393399 @default.
• W4311014196 cites W2065398693 @default.
• W4311014196 cites W2074682976 @default.
• W4311014196 cites W2091893102 @default.
• W4311014196 cites W2107822634 @default.
• W4311014196 cites W2108794978 @default.
• W4311014196 cites W2112420033 @default.
• W4311014196 cites W2124587329 @default.
• W4311014196 cites W2126714083 @default.
• W4311014196 cites W2129131372 @default.
• W4311014196 cites W2147543736 @default.
• W4311014196 cites W2162708633 @default.
• W4311014196 cites W2165612525 @default.
• W4311014196 cites W2168405694 @default.
• W4311014196 cites W2281970206 @default.
• W4311014196 cites W2802230479 @default.
• W4311014196 cites W2883353135 @default.
• W4311014196 cites W2884101506 @default.
• W4311014196 cites W2950929549 @default.
• W4311014196 cites W2963094593 @default.
• W4311014196 cites W2963168238 @default.
• W4311014196 cites W3007054292 @default.
• W4311014196 cites W3025710735 @default.
• W4311014196 cites W3100895096 @default.
• W4311014196 cites W3104999911 @default.
• W4311014196 cites W3106017199 @default.
• W4311014196 cites W3106266785 @default.
• W4311014196 cites W3106279838 @default.
• W4311014196 cites W3124121179 @default.
• W4311014196 cites W4206530644 @default.
• W4311014196 cites W4214481829 @default.
• W4311014196 cites W4246270964 @default.
• W4311014196 doi "https://doi.org/10.1080/01621459.2022.2152343" @default.
• W4311014196 hasPublicationYear "2023" @default.
• W4311014196 type Work @default.
• W4311014196 citedByCount "0" @default.
• W4311014196 crossrefType "journal-article" @default.
• W4311014196 hasAuthorship W4311014196A5035153981 @default.
• W4311014196 hasAuthorship W4311014196A5049225160 @default.
• W4311014196 hasAuthorship W4311014196A5079362198 @default.
• W4311014196 hasBestOaLocation W43110141962 @default.
• W4311014196 hasConcept C11413529 @default.
• W4311014196 hasConcept C119043178 @default.
• W4311014196 hasConcept C119857082 @default.
• W4311014196 hasConcept C126255220 @default.
• W4311014196 hasConcept C134306372 @default.
• W4311014196 hasConcept C154945302 @default.
• W4311014196 hasConcept C182365436 @default.
• W4311014196 hasConcept C2776436953 @default.
• W4311014196 hasConcept C33923547 @default.
• W4311014196 hasConcept C39927690 @default.
• W4311014196 hasConcept C41008148 @default.
• W4311014196 hasConcept C50817715 @default.
• W4311014196 hasConcept C774472 @default.
• W4311014196 hasConceptScore W4311014196C11413529 @default.
• W4311014196 hasConceptScore W4311014196C119043178 @default.
• W4311014196 hasConceptScore W4311014196C119857082 @default.
• W4311014196 hasConceptScore W4311014196C126255220 @default.
• W4311014196 hasConceptScore W4311014196C134306372 @default.
• W4311014196 hasConceptScore W4311014196C154945302 @default.
• W4311014196 hasConceptScore W4311014196C182365436 @default.
• W4311014196 hasConceptScore W4311014196C2776436953 @default.
• W4311014196 hasConceptScore W4311014196C33923547 @default.
• W4311014196 hasConceptScore W4311014196C39927690 @default.
• W4311014196 hasConceptScore W4311014196C41008148 @default.
• W4311014196 hasConceptScore W4311014196C50817715 @default.
• W4311014196 hasConceptScore W4311014196C774472 @default.
• W4311014196 hasFunder F4320320373 @default.
• W4311014196 hasFunder F4320322795 @default.
• W4311014196 hasLocation W43110141961 @default.
• W4311014196 hasLocation W43110141962 @default.
• W4311014196 hasOpenAccess W4311014196 @default.
• W4311014196 hasPrimaryLocation W43110141961 @default.
• W4311014196 hasRelatedWork W2074832029 @default.
• W4311014196 hasRelatedWork W2371270960 @default.
• W4311014196 hasRelatedWork W2947263763 @default.
• W4311014196 hasRelatedWork W2996735312 @default.
• W4311014196 hasRelatedWork W3036260055 @default.
• W4311014196 hasRelatedWork W3094362486 @default.
• W4311014196 hasRelatedWork W3126592115 @default.

• next