Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations

Raphaël Berthier
  • Fonction : Auteur
  • PersonId : 1032278
Francis Bach
  • Fonction : Auteur
  • PersonId : 863086

Résumé

Consider a network of agents connected by communication links, where each agent holds a real value. The gossip problem consists in estimating the average of the values diffused in the network in a distributed manner. We develop a method solving the gossip problem that depends only on the spectral dimension of the network, that is, in the communication network set-up, the dimension of the space in which the agents live. This contrasts with previous work that required the spectral gap of the network as a parameter, or suffered from slow mixing. Our method shows an important improvement over existing algorithms in the non-asymptotic regime, i.e., when the values are far from being fully mixed in the network. Our approach stems from a polynomial-based point of view on gossip algorithms, as well as an approximation of the spectral measure of the graphs with a Jacobi measure. We show the power of the approach with simulations on various graphs, and with performance guarantees on graphs of known spectral dimension, such as grids and random percolation bonds. An extension of this work to distributed Laplacian solvers is discussed. As a side result, we also use the polynomial-based point of view to show the convergence of the message passing algorithm for gossip of Moallemi & Van Roy on regular graphs. The explicit computation of the rate of the convergence shows that message passing has a slow rate of convergence on graphs with small spectral gap.
Fichier principal
Vignette du fichier
paper_gossip_hal.pdf (1.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01797016 , version 1 (22-05-2018)
hal-01797016 , version 2 (15-02-2019)

Identifiants

Citer

Raphaël Berthier, Francis Bach, Pierre Gaillard. Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations. 2019. ⟨hal-01797016v2⟩
312 Consultations
651 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More