Show simple item record

dc.contributor.authorKim, Chiheon
dc.contributor.authorSousa Bandeira, Afonso Jose
dc.contributor.authorGoemans, Michel X
dc.date.accessioned2018-06-05T12:08:06Z
dc.date.available2018-06-05T12:08:06Z
dc.date.issued2017-09
dc.identifier.isbn978-1-5386-1565-2
dc.identifier.urihttp://hdl.handle.net/1721.1/116076
dc.description.abstractWe study the problem of community detection in hypergraphs under a stochastic block model. Similarly to how the stochastic block model in graphs suggests studying spiked random matrices, our model motivates investigating statistical and computational limits of exact recovery in certain spiked tensor models. In contrast with the matrix case, the spiked model naturally arising from community detection in hypergraphs is different from the one arising in the so-called tensor Principal Component Analysis model. We investigate the effectiveness of algorithms in the Sum-of-Squares hierarchy on these models. Interestingly, our results suggest that these two apparently similar models might exhibit very different computational to statistical gaps.en_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/SAMPTA.2017.8024470en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleCommunity detection in hypergraphs, spiked tensor models, and Sum-of-Squaresen_US
dc.typeArticleen_US
dc.identifier.citationKim, Chiheon, Afonso S. Bandeira, and Michel X. Goemans. “Community Detection in Hypergraphs, Spiked Tensor Models, and Sum-of-Squares.” 2017 International Conference on Sampling Theory and Applications (SampTA) (July 2017).en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mathematicsen_US
dc.contributor.mitauthorKim, Chiheon
dc.contributor.mitauthorSousa Bandeira, Afonso Jose
dc.contributor.mitauthorGoemans, Michel X
dc.relation.journal2017 International Conference on Sampling Theory and Applications (SampTA)en_US
dc.eprint.versionOriginal manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2018-05-21T19:20:50Z
dspace.orderedauthorsKim, Chiheon; Bandeira, Afonso S.; Goemans, Michel X.en_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-3705-5318
dc.identifier.orcidhttps://orcid.org/0000-0002-7331-7557
dc.identifier.orcidhttps://orcid.org/0000-0002-0520-1165
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record