Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  PAC-Bayesian Analysis of Contextual Bandits

Seldin, Y., Auer, P., Laviolette, F., Shawe-Taylor, J., & Ortner, R. (2012). PAC-Bayesian Analysis of Contextual Bandits. In J. Shaw-Taylor, R. Zemel, P. Bartlett, F. Pereira, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems 24 (pp. 1683-1691). Red Hook, NY, USA: Curran.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-B884-D Versions-Permalink: https://hdl.handle.net/21.11116/0000-0001-1958-1
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://papers.nips.cc/paper/4227-pac-bayesian-analysis-of-contextual-bandits.pdf (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Seldin, Y1, Autor           
Auer, P, Autor
Laviolette, F, Autor
Shawe-Taylor, J, Autor
Ortner, R, Autor
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, DE, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We derive an instantaneous (per-round) data-dependent regret bound for stochastic multiarmed bandits with side information (also known as contextual bandits). The scaling of our regret bound with the number of states (contexts) N goes as \sqrtN I_{ρ_t}(S;A)}, where I_{ρ_t}(S;A) is the mutual information between states and actions (the side information) used by the algorithm at round t. If the algorithm uses all the side information, the regret bound scales as \sqrt{N \ln K}, where K is the number of actions (arms). However, if the side information I_{ρ_t}(S;A) is not fully used, the regret bound is significantly tighter. In the extreme case, when I_{ρ_t(S;A) = 0, the dependence on the number of states reduces from linear to logarithmic. Our analysis allows to provide the algorithm large amount of side information, let the algorithm to decide which side information is relevant for the task, and penalize the algorithm only for the side information that it is using de facto. We also present an algorithm for multiarmed bandits with side information with computational complexity that is a linear in the number of actions.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2012-01
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: SeldinALSO2011
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011)
Veranstaltungsort: Granada, Spain
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Advances in Neural Information Processing Systems 24
Genre der Quelle: Konferenzband
 Urheber:
Shaw-Taylor, J, Herausgeber
Zemel, RS, Herausgeber
Bartlett, P, Herausgeber
Pereira, F, Herausgeber
Weinberger, KQ, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Red Hook, NY, USA : Curran
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1683 - 1691 Identifikator: ISBN: 978-1-618-39599-3