de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84206

Seldin,  Y
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Seldin, Y., Cesa-Bianchi N, Auer P, Laviolette, F., & Shawe-Taylor, J. (2012). PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits. In JMLR Workshop and Conference Proceedings 26 (pp. 1-14). Cambridge, MA, USA: JMLR.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-0013-B7EC-F
Zusammenfassung
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The first ingredient is a new concentration inequality that makes it possible to control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. The second ingredient is an application of this inequality to the exploration-exploitation trade-off via importance weighted sampling. We apply the new tool to the stochastic multiarmed bandit problem, however, the main importance of this paper is the development and understanding of the new tool rather than improvement of existing algorithms for stochastic multiarmed bandits. In the follow-up work we demonstrate that the new tool can improve over state-of-the-art in structurally richer problems, such as stochastic multiarmed bandits with side information (Seldin et al., 2011a).