From bandits to experts: A tale of domination and independence

Noga Alon; Nicolò Cesa-Bianchi; Claudio Gentile; Yishay Mansour

From bandits to experts: A tale of domination and independence

Noga Alon
, Nicolò Cesa-Bianchi
, Claudio Gentile
, Yishay Mansour

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

61 Scopus citations

Abstract

We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph (which must be accessible before selecting an action). In the undirected case, we show that the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-efficient manner.

Original language	English
Journal	Advances in Neural Information Processing Systems
State	Published - 1 Jan 2013
Externally published	Yes
Event	27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States Duration: 5 Dec 2013 → 10 Dec 2013

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{eadf7bfac6d94cd3aae8549545cc2ef2,

title = "From bandits to experts: A tale of domination and independence",

abstract = "We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph (which must be accessible before selecting an action). In the undirected case, we show that the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-efficient manner.",

author = "Noga Alon and Nicol{\`o} Cesa-Bianchi and Claudio Gentile and Yishay Mansour",

year = "2013",

month = jan,

day = "1",

language = "English",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

note = "27th Annual Conference on Neural Information Processing Systems, NIPS 2013 ; Conference date: 05-12-2013 Through 10-12-2013",

}

TY - JOUR

T1 - From bandits to experts

T2 - 27th Annual Conference on Neural Information Processing Systems, NIPS 2013

AU - Alon, Noga

AU - Cesa-Bianchi, Nicolò

AU - Gentile, Claudio

AU - Mansour, Yishay

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph (which must be accessible before selecting an action). In the undirected case, we show that the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-efficient manner.

AB - We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph (which must be accessible before selecting an action). In the undirected case, we show that the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-efficient manner.

UR - https://www.scopus.com/pages/publications/84898993906

M3 - Conference article

AN - SCOPUS:84898993906

SN - 1049-5258

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

Y2 - 5 December 2013 through 10 December 2013

ER -

From bandits to experts: A tale of domination and independence

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this