Better Algorithms for Stochastic Bandits with Adversarial Corruptions

Anupam Gupta; Tomer Koren; Kunal Talwar

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

Anupam Gupta, Tomer Koren, Kunal Talwar

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

72 Scopus citations

Abstract

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount of corruption with virtually no degradation in performance.

Original language	English
Pages (from-to)	1562-1578
Number of pages	17
Journal	Proceedings of Machine Learning Research
Volume	99
State	Published - 2019
Externally published	Yes
Event	32nd Conference on Learning Theory, COLT 2019 - Phoenix, United States Duration: 25 Jun 2019 → 28 Jun 2019

Funding

Funders	Funder number
National Science Foundation	CCF-1536002, CCF-1617790, CCF-1540541

Cite this

@article{d72f30ef4c4d4bcb97fbd6840cd0d2b2,

title = "Better Algorithms for Stochastic Bandits with Adversarial Corruptions",

abstract = "We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount of corruption with virtually no degradation in performance.",

author = "Anupam Gupta and Tomer Koren and Kunal Talwar",

note = "Publisher Copyright: {\textcopyright} 2019 A. Gupta, T. Koren & K. Talwar.; 32nd Conference on Learning Theory, COLT 2019 ; Conference date: 25-06-2019 Through 28-06-2019",

year = "2019",

language = "אנגלית",

volume = "99",

pages = "1562--1578",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

}

TY - JOUR

T1 - Better Algorithms for Stochastic Bandits with Adversarial Corruptions

AU - Gupta, Anupam

AU - Koren, Tomer

AU - Talwar, Kunal

PY - 2019

Y1 - 2019

N2 - We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount of corruption with virtually no degradation in performance.

AB - We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount of corruption with virtually no degradation in performance.

UR - http://www.scopus.com/inward/record.url?scp=85160843794&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:85160843794

SN - 2640-3498

VL - 99

SP - 1562

EP - 1578

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 32nd Conference on Learning Theory, COLT 2019

Y2 - 25 June 2019 through 28 June 2019

ER -

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

Abstract

Funding

Other files and links

Fingerprint

Cite this