A convex formulation for learning scale-free networks via submodular relaxation

dc.contributor.authorDefazio, Aaron
dc.contributor.authorCaetano, Tiberio
dc.coverage.spatialLake Tahoe Nevada USA
dc.date.accessioned2015-12-13T22:56:14Z
dc.date.createdDecember 3-6 2012
dc.date.issued2012
dc.date.updated2016-02-24T08:37:36Z
dc.description.abstractA key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is known to be scale-free. We show that in such cases it is natural to formulat
dc.identifier.isbn9781627480031
dc.identifier.urihttp://hdl.handle.net/1885/82731
dc.publisherNeural Information Processing Systems Foundation
dc.relation.ispartofseriesNeural Information Processing Systems Conference (NIPS 2012)
dc.rightsAuthor/s retain copyrighten_AU
dc.sourceNEURAL INFORMATION PROCESSING SYSTEMS. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012
dc.source.urihttp://www.proceedings.com/17576.html
dc.source.urihttp://arxiv.org/abs/1407.2697
dc.subjectKeywords: Convex optimization problems; Convex relaxation; Gaussian graphical models; Network structures; Scale free networks; Structured sparsities; Submodular functions; Tractable class; Convex optimization; Relaxation processes
dc.titleA convex formulation for learning scale-free networks via submodular relaxation
dc.typeConference paper
dcterms.accessRightsOpen Accessen_AU
local.bibliographicCitation.lastpage1258
local.bibliographicCitation.startpage1250
local.contributor.affiliationDefazio, Aaron, College of Engineering and Computer Science, ANU
local.contributor.affiliationCaetano, Tiberio, College of Engineering and Computer Science, ANU
local.contributor.authoremailu4406979@anu.edu.au
local.contributor.authoruidDefazio, Aaron, u4406979
local.contributor.authoruidCaetano, Tiberio, u4590840
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor020100 - ASTRONOMICAL AND SPACE SCIENCES
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationf5625xPUB10941
local.identifier.scopusID2-s2.0-84877737602
local.identifier.uidSubmittedByf5625
local.type.statusPublished Version

Downloads

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
01_Defazio_A_convex_formulation_for_2012.pdf
Size:
385.59 KB
Format:
Adobe Portable Document Format