Corralling Stochastic Bandit Algorithms

Raman Arora; Teodor V. Marinov; Mehryar Mohri

Corralling Stochastic Bandit Algorithms

Raman Arora, Teodor V. Marinov, Mehryar Mohri

Computer Science

Research output: Contribution to journal › Conference article › peer-review

Abstract

We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.

Original language	English (US)
Pages (from-to)	2116-2124
Number of pages	9
Journal	Proceedings of Machine Learning Research
Volume	130
State	Published - 2021
Event	24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, United States Duration: Apr 13 2021 → Apr 15 2021

ASJC Scopus subject areas

Artificial Intelligence
Software
Control and Systems Engineering
Statistics and Probability

Cite this

@article{61dc352f9405421fae3d169824c70b11,

title = "Corralling Stochastic Bandit Algorithms",

abstract = "We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.",

author = "Raman Arora and Marinov, {Teodor V.} and Mehryar Mohri",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 by the author(s); 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 ; Conference date: 13-04-2021 Through 15-04-2021",

year = "2021",

language = "English (US)",

volume = "130",

pages = "2116--2124",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Corralling Stochastic Bandit Algorithms

AU - Arora, Raman

AU - Marinov, Teodor V.

AU - Mohri, Mehryar

PY - 2021

Y1 - 2021

N2 - We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.

AB - We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.

UR - http://www.scopus.com/inward/record.url?scp=85161884279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85161884279&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85161884279

SN - 2640-3498

VL - 130

SP - 2116

EP - 2124

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021

Y2 - 13 April 2021 through 15 April 2021

ER -

Corralling Stochastic Bandit Algorithms

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this