Clustering from sparse pairwise measurements

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download
Contributor : Marc Lelarge <>
Submitted on : Thursday, November 3, 2016 - 3:17:59 PM
Last modification on : Thursday, October 17, 2019 - 12:36:04 PM
Long-term archiving on: Saturday, February 4, 2017 - 1:53:07 PM


Files produced by the author(s)



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⟩



Record views


Files downloads