Clustering from sparse pairwise measurements - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Clustering from sparse pairwise measurements

Résumé

We consider the problem of grouping items into clusters based on few random pairwise comparisons between the items. We introduce three closely related algorithms for this task: a belief propagation algorithm approximating the Bayes optimal solution, and two spectral algorithms based on the non-backtracking and Bethe Hessian operators. For the case of two symmetric clusters, we conjecture that these algorithms are asymptotically optimal in that they detect the clusters as soon as it is information theoretically possible to do so. We substantiate this claim for one of the spectral approaches we introduce.
Fichier principal
Vignette du fichier
1601.06683v2.pdf (1.48 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01391585 , version 1 (03-11-2016)

Identifiants

Citer

Alaa Saade, Florent Krzakala, Marc Lelarge, Lenka Zdeborová. Clustering from sparse pairwise measurements. 2016 IEEE International Symposium on Information Theory (ISIT 2016), Jul 2016, Barcelone, Spain. pp.780 - 784, ⟨10.1109/ISIT.2016.7541405⟩. ⟨hal-01391585⟩
640 Consultations
121 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More