Collaborative distributed hypothesis testing - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Collaborative distributed hypothesis testing

Gil Katz
  • Fonction : Auteur
  • PersonId : 962724
Merouane Debbah
  • Fonction : Auteur
  • PersonId : 863308

Résumé

A collaborative distributed binary decision problem is considered. Two statisticians are required to declare the correct probability measure of two jointly distributed memoryless process, denoted by Xn=(X1,…,Xn) and Yn=(Y1,…,Yn), out of two possible probability measures on finite alphabets, namely PXY and PX¯Y¯. The marginal samples given by Xn and Yn are assumed to be available at different locations. The statisticians are allowed to exchange limited amount of data over multiple rounds of interactions, which differs from previous work that deals mainly with unidirectional communication. A single round of interaction is considered before the result is generalized to any finite number of communication rounds. A feasibility result is shown, guaranteeing the feasibility of an error exponent for general hypotheses, through information-theoretic methods. The special case of testing against independence is revisited as being an instance of this result for which also an unfeasibility result is proven. A second special case is studied where zero-rate communication is imposed (data exchanges grow sub-exponentially with n) for which it is shown that interaction does not improve asymptotic performance.
Fichier principal
Vignette du fichier
AoS2016_debbah.pdf (505.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01436767 , version 1 (18-06-2020)

Identifiants

Citer

Gil Katz, Pablo Piantanida, Merouane Debbah. Collaborative distributed hypothesis testing. 2016. ⟨hal-01436767⟩
129 Consultations
29 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More