Paper published in a book (Scientific congresses and symposiums)
Optimal discovery with probabilistic expert advice
Bubeck, Sébastien; Ernst, Damien; Garivier, Aurélien
2012In Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012)
Peer reviewed
 

Files


Full Text
0810.pdf
Publisher postprint (245.25 kB)
Download
Annexes
BEG11.pdf
Publisher postprint (300.77 kB)
Extended version of the paper
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Optimal discovery; Probabilistic expert advice
Abstract :
[en] Motivated by issues of security analysis for power systems, we analyze a new problem, called optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and the Good-Turingmissing mass estimator. We show that this strategy attains the optimal discovery rate in a macroscopic limit sense, under some assumptions on the probabilistic experts. We also provide numerical experiments suggesting that this optimal behavior may still hold under weaker assumptions.
Disciplines :
Computer science
Author, co-author :
Bubeck, Sébastien
Ernst, Damien  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids
Garivier, Aurélien
Language :
English
Title :
Optimal discovery with probabilistic expert advice
Publication date :
December 2012
Event name :
51st IEEE Conference on Decision and Control (CDC 2012)
Event place :
Maui, Hawaii, United States
Event date :
December 10-13, 2012
Audience :
International
Main work title :
Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012)
Peer reviewed :
Peer reviewed
Available on ORBi :
since 28 December 2012

Statistics


Number of views
61 (2 by ULiège)
Number of downloads
185 (1 by ULiège)

Scopus citations®
 
0
Scopus citations®
without self-citations
0

Bibliography


Similar publications



Contact ORBi