Reference : Optimal discovery with probabilistic expert advice
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
Optimal discovery with probabilistic expert advice
Bubeck, Sébastien []
Ernst, Damien mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Garivier, Aurélien []
Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012)
51st IEEE Conference on Decision and Control (CDC 2012)
December 10-13, 2012
Maui, Hawaii
[en] Optimal discovery ; Probabilistic expert advice
[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.
Researchers ; Professionals ; Students

File(s) associated to this reference

Fulltext file(s):

Open access
0810.pdfPublisher postprint239.5 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
BEG11.pdfExtended version of the paper293.72 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.