Optimality of variational inference for stochastic block model with missing links - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Optimality of variational inference for stochastic block model with missing links

Abstract

Variational methods are extremely popular in the analysis of network data. Statistical guarantees obtained for these methods typically provide asymptotic normality for the problem of estimation of global model parameters under the stochastic block model. In the present work, we consider the case of networks with missing links that is important in application and show that the variational approximation to the maximum likelihood estimator converges at the minimax rate. This provides the first minimax optimal and tractable estimator for the problem of parameter estimation for the stochastic block model with missing links. We complement our results with numerical studies of simulated and real networks, which confirm the advantages of this estimator over current methods.
Fichier principal
Vignette du fichier
main.pdf (681.13 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03393160 , version 1 (21-10-2021)
hal-03393160 , version 2 (04-11-2021)

Identifiers

Cite

Solenne Gaucher, Olga Klopp. Optimality of variational inference for stochastic block model with missing links. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, Online, France. ⟨10.48550/arXiv.2111.03305⟩. ⟨hal-03393160v2⟩
98 View
73 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More