Pairwise MRF Models Selection for Traffic Inference - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Interdisciplinary Information Sciences Year : 2013

Pairwise MRF Models Selection for Traffic Inference

Cyril Furtlehner

Abstract

We survey some recent work where, motivated by traffic inference, we design in parallel two concurrent models, an Ising and a Gaussian ones, with the constraint that they are suitable for ''belief-propagation'' based inference. In order to build these model, we study how a Bethe mean-field solution to inverse problems obtained with a maximum spanning tree of pairwise mutual information, can serve as a reference point for further perturbation procedures. We consider three different ways along this idea: the first one is based on an explicit natural gradient formula; the second one is a link by link construction based on iterative proportional scaling; the last one relies on a duality transformation leading to a loop correction propagation algorithm on a dual factor graph.
Fichier principal
Vignette du fichier
iis2012-draft.pdf (123.39 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00865089 , version 1 (24-09-2013)

Identifiers

Cite

Cyril Furtlehner. Pairwise MRF Models Selection for Traffic Inference. Interdisciplinary Information Sciences, 2013, Special Issue: The 4th Young Scientist Meeting on Statistical Physics and Information Processing in Sendai, 19 (1), pp.17-22. ⟨10.4036/iis.2013.17⟩. ⟨hal-00865089⟩
322 View
218 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More