Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  PAC-Bayesian Analysis of Martingales and Multiarmed Bandits

Seldin, Y., Laciolette, F., Shaw-Taylor, J., Peters, J., & Auer, P.(2011). PAC-Bayesian Analysis of Martingales and Multiarmed Bandits. Tübingen, Germany: Max Planck Institute for Biological Cybernetics.

Item is

Dateien

einblenden: Dateien
ausblenden: Dateien
:
TR-2011-Seldin.pdf (beliebiger Volltext), 235KB
Name:
TR-2011-Seldin.pdf
Beschreibung:
-
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
-

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
http://arxiv.org/abs/1105.2416 (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Seldin, Y1, 2, Autor           
Laciolette, F, Autor
Shaw-Taylor, J, Autor
Peters, J.1, 2, Autor           
Auer, P, Autor
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by expectations of the same functions of independent Bernoulli random variables. This lemma provides an alternative tool to Hoeffding-Azuma inequality to bound concentration of martingale values. Our second approach is based on integration of Hoeffding-Azuma inequality with PAC-Bayesian analysis. We also introduce a way to apply PAC-Bayesian analysis in situation of limited feedback. We combine the new tools to derive PAC-Bayesian generalization and regret bounds for the multiarmed bandit problem. Although our regret bound is not yet as tight as state-of-the-art regret bounds based on other well-established techniques, our results significantly expand the range of potential applications of PAC-Bayesian analysis and introduce a new analysis tool to reinforcement learning and many other fields, where martingales and limited feedback are encountered.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2011-05
 Publikationsstatus: Erschienen
 Seiten: 13
 Ort, Verlag, Ausgabe: Tübingen, Germany : Max Planck Institute for Biological Cybernetics
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: SeldinLSPA2011
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Technical Reports of the Max Planck Institute for Biological Cybernetics
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -