Extending Gossip Algorithms to Distributed Estimation of U-statistics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Extending Gossip Algorithms to Distributed Estimation of U-statistics

Abstract

Efficient and robust algorithms for decentralized estimation in networks are essential to many distributed systems. Whereas distributed estimation of sample mean statistics has been the subject of a good deal of attention, computation of U-statistics, relying on more expensive averaging over pairs of observations, is a less investigated area. Yet, such data functionals are essential to describe global properties of a statistical population, with important examples including Area Under the Curve, empirical variance, Gini mean difference and within-cluster point scatter. This paper proposes new synchronous and asynchronous randomized gossip algorithms which simultaneously propagate data across the network and maintain local estimates of the U-statistic of interest. We establish convergence rate bounds of O(1 / t) and O(log t / t) for the synchronous and asynchronous cases respectively, where t is the number of iterations, with explicit data and network dependent terms. Beyond favorable comparisons in terms of rate analysis, numerical experiments provide empirical evidence the proposed algorithms surpasses the previously introduced approach.
Fichier principal
Vignette du fichier
nips15_gossip.pdf (473.53 Ko) Télécharger le fichier
nips15_gossip_supp.pdf (650.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01214665 , version 1 (05-11-2015)

Identifiers

  • HAL Id : hal-01214665 , version 1

Cite

Igor Colin, Aurélien Bellet, Joseph Salmon, Stéphan Clémençon. Extending Gossip Algorithms to Distributed Estimation of U-statistics. Annual Conference on Neural Information Processing Systems (NIPS), Dec 2015, Montréal, Canada. ⟨hal-01214665⟩
433 View
84 Download

Share

Gmail Facebook X LinkedIn More