Optimal graphon estimation in cut distance - ESSEC Business School Accéder directement au contenu
Article Dans Une Revue Probability Theory and Related Fields Année : 2019

Optimal graphon estimation in cut distance

Résumé

Consider the twin problems of estimating the connection probability matrix of an inhomogeneous random graph and the graphon of a W-random graph. We establish the minimax estimation rates with respect to the cut metric for classes of block constant matrices and step function graphons. Surprisingly, our results imply that, from the minimax point of view, the raw data, that is, the adjacency matrix of the observed graph, is already optimal and more involved procedures cannot improve the convergence rates for this metric. This phenomenon contrasts with optimal rates of convergence with respect to other classical distances for graphons such as the l 1 or l 2 metrics.
Fichier principal
Vignette du fichier
cut_norm_revision1.pdf (532.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01490371 , version 1 (15-03-2017)
hal-01490371 , version 2 (14-10-2018)

Identifiants

Citer

Olga Klopp, Nicolas Verzelen. Optimal graphon estimation in cut distance. Probability Theory and Related Fields, 2019, 174 (3-4), pp.1033-1090. ⟨10.1007/s00440-018-0878-1⟩. ⟨hal-01490371v2⟩
464 Consultations
983 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More